# Computer Science

## New submissions

[ total of 298 entries: 1-298 ]
[ showing up to 2000 entries per page: fewer | more ]

### New submissions for Thu, 22 Aug 19

[1]
Title: AI for Earth: Rainforest Conservation by Acoustic Surveillance
Comments: Accepted to KDD2019 Workshop on Data Mining and AI for Conservation
Subjects: Sound (cs.SD); Databases (cs.DB); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)

Saving rainforests is a key to halting adverse climate changes. In this paper, we introduce an innovative solution built on acoustic surveillance and machine learning technologies to help rainforest conservation. In particular, We propose new convolutional neural network (CNN) models for environmental sound classification and achieved promising preliminary results on two datasets, including a public audio dataset and our real rainforest sound dataset. The proposed audio classification models can be easily extended in an automated machine learning paradigm and integrated in cloud-based services for real world deployment.

[2]
Title: Multi-Modal Recognition of Worker Activity for Human-Centered Intelligent Manufacturing
Comments: 17 pages, 8 figures, 6 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Image and Video Processing (eess.IV); Signal Processing (eess.SP)

In a human-centered intelligent manufacturing system, sensing and understanding of the worker's activity are the primary tasks. In this paper, we propose a novel multi-modal approach for worker activity recognition by leveraging information from different sensors and in different modalities. Specifically, a smart armband and a visual camera are applied to capture Inertial Measurement Unit (IMU) signals and videos, respectively. For the IMU signals, we design two novel feature transform mechanisms, in both frequency and spatial domains, to assemble the captured IMU signals as images, which allow using convolutional neural networks to learn the most discriminative features. Along with the above two modalities, we propose two other modalities for the video data, at the video frame and video clip levels, respectively. Each of the four modalities returns a probability distribution on activity prediction. Then, these probability distributions are fused to output the worker activity classification result. A worker activity dataset of 6 activities is established, which at present contains 6 common activities in assembly tasks, i.e., grab a tool/part, hammer a nail, use a power-screwdriver, rest arms, turn a screwdriver, and use a wrench. The developed multi-modal approach is evaluated on this dataset and achieves recognition accuracies as high as 97% and 100% in the leave-one-out and half-half experiments, respectively.

[3]
Title: Preserving Command Line Workflow for a Package Management System using ASCII DAG Visualization
Journal-ref: Volume: 25, Issue: 9, Sept. 1 2019, Pages: 2804 - 2820
Subjects: Human-Computer Interaction (cs.HC)

Package managers provide ease of access to applications by removing the time-consuming and sometimes completely prohibitive barrier of successfully building, installing, and maintaining the software for a system. A package dependency contains dependencies between all packages required to build and run the target software. Package management system developers, package maintainers, and users may consult the dependency graph when a simple listing is insufficient for their analyses. However, users working in a remote command line environment must disrupt their workflow to visualize dependency graphs in graphical programs, possibly needing to move files between devices or incur forwarding lag. Such is the case for users of Spack, an open source package management system originally developed to ease the complex builds required by supercomputing environments. To preserve the command line workflow of Spack, we develop an interactive ASCII visualization for its dependency graphs. Through interviews with Spack maintainers, we identify user goals and corresponding visual tasks for dependency graphs. We evaluate the use of our visualization through a command line-centered study, comparing it to the system's two existing approaches. We observe that despite the limitations of the ASCII representation, our visualization is preferred by participants when approached from a command line interface workflow.

[4]
Title: Phrase Localization Without Paired Training Examples
Comments: Accepted for oral presentation at the IEEE/CVF International Conference on Computer Vision (ICCV) 2019
Subjects: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Machine Learning (cs.LG)

Localizing phrases in images is an important part of image understanding and can be useful in many applications that require mappings between textual and visual information. Existing work attempts to learn these mappings from examples of phrase-image region correspondences (strong supervision) or from phrase-image pairs (weak supervision). We postulate that such paired annotations are unnecessary, and propose the first method for the phrase localization problem where neither training procedure nor paired, task-specific data is required. Our method is simple but effective: we use off-the-shelf approaches to detect objects, scenes and colours in images, and explore different approaches to measure semantic similarity between the categories of detected visual elements and words in phrases. Experiments on two well-known phrase localization datasets show that this approach surpasses all weakly supervised methods by a large margin and performs very competitively to strongly supervised methods, and can thus be considered a strong baseline to the task. The non-paired nature of our method makes it applicable to any domain and where no paired phrase localization annotation is available.

[5]
Title: Robust Graph Neural Network Against Poisoning Attacks via Transfer Learning
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR); Social and Information Networks (cs.SI); Machine Learning (stat.ML)

Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal features can significantly reduce the performances of GNNs. It is very challenging to design robust graph neural networks against poisoning attack and several efforts have been taken. Existing work aims at reducing the negative impact from adversarial edges only with the poisoned graph, which is sub-optimal since they fail to discriminate adversarial edges from normal ones. On the other hand, clean graphs from similar domains as the target poisoned graph are usually available in the real world. By perturbing these clean graphs, we create supervised knowledge to train the ability to detect adversarial edges so that the robustness of GNNs is elevated. However, such potential for clean graphs is neglected by existing work. To this end, we investigate a novel problem of improving the robustness of GNNs against poisoning attacks by exploring clean graphs. Specifically, we propose PA-GNN, which relies on a penalized aggregation mechanism that directly restrict the negative impact of adversarial edges by assigning them lower attention coefficients. To optimize PA-GNN for a poisoned graph, we design a meta-optimization algorithm that trains PA-GNN to penalize perturbations using clean graphs and their adversarial counterparts, and transfers such ability to improve the robustness of PA-GNN on the poisoned graph. Experimental results on four real-world datasets demonstrate the robustness of PA-GNN against poisoning attacks on graphs.

[6]
Title: Reactive Probabilistic Programming
Subjects: Programming Languages (cs.PL)

Synchronous reactive languages were introduced for designing and implementing real-time control software. These domain-specific languages allow for writing a modular and mathematically precise specification of the system, enabling a user to simulate, test, verify, and, finally, compile the system into executable code. However, to date these languages have had limited modern support for modeling uncertainty -- probabilistic aspects of the software's environment or behavior -- even though modeling uncertainty is a primary activity when designing a control system.
In this paper we extend Z\'elus, a synchronous programming language, to deliver ProbZ\'elus, the first synchronous probabilistic programming language. ProbZ\'elus is a probabilistic programming language in that it provides facilities for probabilistic models and inference: inferring latent model parameters from data.
We present ProbZ\'elus's measure-theoretic semantics in the setting of probabilistic, stateful stream functions. We then demonstrate a semantics-preserving compilation strategy to a first-order functional core calculus that lends itself to a simple semantic presentation of ProbZ\'elus's inference algorithms. We also redesign the delayed sampling inference algorithm to provide bounded and streaming delayed sampling inference for ProbZ\'elus models. Together with our evaluation on several reactive programs, our results demonstrate that ProbZ\'elus provides efficient, bounded memory probabilistic inference.

[7]
Title: Predicting publication productivity for researchers: a piecewise Poisson model
Authors: Zheng Xie
Subjects: Digital Libraries (cs.DL); Physics and Society (physics.soc-ph)

Predicting the scientific productivity of researchers is a basic task for academic administrators and funding agencies. This study provided a model for the publication dynamics of researchers, inspired by the distribution feature of researchers' publications in quantity. It is a piecewise Poisson model, analyzing and predicting the publication productivity of researchers by regression. The principle of the model is built on the explanation for the distribution feature as a result of an inhomogeneous Poisson process that can be approximated as a piecewise Poisson process. The model's principle was validated by the high quality dblp dataset, and its effectiveness was testified in predicting the publication productivity for majority of researchers and the evolutionary trend of their publication productivity. Tests to confirm or disconfirm the model are also proposed. The model has the advantage of providing results in an unbiased way; thus is useful for funding agencies that evaluate a vast number of applications with a quantitative index on publications.

[8]
Title: Finding the right scale of a network: Efficient identification of causal emergence through spectral clustering
Subjects: Social and Information Networks (cs.SI); Physics and Society (physics.soc-ph)

All networks can be analyzed at multiple scales. A higher scale of a network is made up of macro-nodes: subgraphs that have been grouped into individual nodes. Recasting a network at higher scales can have useful effects, such as decreasing the uncertainty in the movement of random walkers across the network while also decreasing the size of the network. However, the task of finding such a macroscale representation is computationally difficult, as the set of all possible scales of a network grows exponentially with the number of nodes. Here we compare various methods for finding the most informative scale of a network, discovering that an approach based on spectral analysis outperforms greedy and gradient descent-based methods. We then use this procedure to show how several structural properties of preferential attachment networks vary across scales. We describe how meso- and macroscale representations of networks can have significant benefits over their underlying microscale, which include properties such as increase in determinism, a decrease in degeneracy, a lower entropy rate of random walkers on the network, an increase in global network efficiency, and higher values for a variety of centrality measures than the microscale.

[9]
Title: Eunomia: A Permissionless Parallel Chain Protocol Based on Logical Clock
Authors: Jianyu Niu
Comments: 19 pages, 5 figures, technical report
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Cryptography and Security (cs.CR)

The emerging parallel chain protocols represent a breakthrough to address the scalability of blockchain. By composing multiple parallel chain instances, the whole systems' throughput can approach the network capacity. How to coordinate different chains' blocks and to construct them into a global ordering is critical to the performance of parallel chain protocol. However, the existed solutions use either the global synchronization clock with the single-chain bottleneck or pre-defined ordering sequences with distortion of blocks' causality to order blocks. In addition, the prior ordering methods rely on that honest participants faithfully follow the ordering protocol, but remain silent for any denial of ordering (DoR) attack.
On the other hand, the conflicting transactions included into the global block sequence will make Simple Payment Verification (SPV) difficult. Clients usually need to store a full record of transactions to distinguish the conflictions and tell whether transactions are confirmed. However, the requirement for a full record will greatly hinder blockchains' application, especially for mobile scenarios.
In this technical report, we propose Eunomia, which leverages logical clock and fine-grained UTXO sharding to realize a simple, efficient, secure and permissionless parallel chain protocol. By observing the characteristics of the parallel chain, we find the blocks ordering issue in parallel chain has many similarities with the event ordering in the distributed system. Eunomia thus adopts "virtual" logical clock, which is optimized to have the minimum protocol overhead and runs in a distributed way. In addition, Eunomia combines the mining incentive with block ordering, providing incentive compatibility against DoR attack. What's more, the fine-grained UTXO sharding does well solve the conflicting transactions in parallel chain and is shown to be SPV-friendly.

[10]
Subjects: Human-Computer Interaction (cs.HC); Robotics (cs.RO)

One of the challenges in conducting research on the intersection of the CHI and Human-Robot Interaction (HRI) communities is in addressing the gap of acceptable design research methods between the two. While HRI is focused on interaction with robots and includes design research in its scope, the community is not as accustomed to exploratory design methods as the CHI community. This workshop paper argues for bringing exploratory design, and specifically Research through Design (RtD) methods that have been established in CHI for the past decade to the foreground of HRI. RtD can enable design researchers in the field of HRI to conduct exploratory design work that asks what is the right thing to design and share it within the community.

[11]
Title: Securing HPC using Federated Authentication
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Cryptography and Security (cs.CR)

Federated authentication can drastically reduce the overhead of basic account maintenance while simultaneously improving overall system security. Integrating with the user's more frequently used account at their primary organization both provides a better experience to the end user and makes account compromise or changes in affiliation more likely to be noticed and acted upon. Additionally, with many organizations transitioning to multi-factor authentication for all account access, the ability to leverage external federated identity management systems provides the benefit of their efforts without the additional overhead of separately implementing a distinct multi-factor authentication process. This paper describes our experiences and the lessons we learned by enabling federated authentication with the U.S. Government PKI and InCommon Federation, scaling it up to the user base of a production HPC system, and the motivations behind those choices. We have received only positive feedback from our users.

[12]
Title: The citation advantage of foreign language references for Chinese social science papers
Comments: 24 pages, 9 figures, 10 tables
Journal-ref: Scientometrics,2019,120(3):1439-1460
Subjects: Digital Libraries (cs.DL)

Contemporary scientific exchanges are international, yet language continues to be a persistent barrier to scientific communication, particularly for non-native English-speaking scholars. Since the ability to absorb knowledge has a strong impact on how researchers create new scientific knowledge, a comprehensive access to and understanding of both domestic and international scientific publications is essential for scientific performance. This study explores the effect of absorbed knowledge on research impact by analyzing the relationship between the language diversity of cited references and the number of citations received by the citing paper. Chinese social sciences are taken as the research object, and the data, 950,302 papers published between 1998 and 2013 with 8,151,327 cited references, were collected from the Chinese Social Sciences Citation Index. Results show that there is a stark increase in the consumption of foreign language material within the Chinese social science community, and English material accounts for the vast majority of this consumption. Papers with foreign language references receive significantly more citations than those without, and the citation advantage of these internationalized work holds when we control for characteristics of the citing papers. However, the citation advantage has decreased from 1998 to 2008, largely as an artifact of the increased number of papers citing foreign language material. After 2008, the decline of the citation advantage subsided and became relatively stable, which suggests that incorporating foreign language literature continues to increase scientific impact, even as the scientific community itself becomes increasingly international. However, internationalization is not without concerns: the work closes with a discussion of the benefits and potential problems of the lack of linguistic diversity in scientific communication.

[13]
Title: Challenges of Designing HCI for Negative Emotions
Subjects: Human-Computer Interaction (cs.HC)

Emotions that are perceived as "negative" are inherent in the human experience. Yet not much work in the field of HCI has looked into the role of these emotions in interaction with technology. As technology is becoming more social, personal and emotional by mediating our relationships and generating new social entities (such as conversational agents and robots), it is valuable to consider how it can support people's negative emotions and behaviors. Research in Psychology shows that interacting with negative emotions correctly can benefit well-being, yet the boundary between helpful and harmful is delicate. This workshop paper looks at the opportunities of designing for negative affect, and the challenge of "causing no harm" that arises in an attempt to do so.

[14]
Title: Realistic versus Rational Secret Sharing
Comments: This is a preliminary version of a paper accepted for GameSec 2019
Subjects: Cryptography and Security (cs.CR); Theoretical Economics (econ.TH)

The study of Rational Secret Sharing initiated by Halpern and Teague regards the reconstruction of the secret in secret sharing as a game. It was shown that participants (parties) may refuse to reveal their shares and so the reconstruction may fail. Moreover, a refusal to reveal the share may be a dominant strategy of a party.
In this paper we consider secret sharing as a sub-action or subgame of a larger action/game where the secret opens a possibility of consumption of a certain common good. We claim that utilities of participants will be dependent on the nature of this common good. In particular, Halpern and Teague scenario corresponds to a rivalrous and excludable common good. We consider the case when this common good is non-rivalrous and non-excludable and find many natural Nash equilibria. We list several applications of secret sharing to demonstrate our claim and give corresponding scenarios. In such circumstances the secret sharing scheme facilitates a power sharing agreement in the society. We also state that non-reconstruction may be beneficial for this society and give several examples.

[15]
Title: Optimization Bounds from the Branching Dual
Journal-ref: INFORMS Journal on Computing, published online 19 July 2019
Subjects: Data Structures and Algorithms (cs.DS)

We present a general method for obtaining strong bounds for discrete optimization problems that is based on a concept of branching duality. It can be applied when no useful integer programming model is available, and we illustrate this with the minimum bandwidth problem. The method strengthens a known bound for a given problem by formulating a dual problem whose feasible solutions are partial branching trees. It solves the dual problem with a "worst-bound" local search heuristic that explores neighboring partial trees. After proving some optimality properties of the heuristic, we show that it substantially improves known combinatorial bounds for the minimum bandwidth problem with a modest amount of computation. It also obtains significantly tighter bounds than depth-first and breadth-first branching, demonstrating that the dual perspective can lead to better branching strategies when the object is to find valid bounds.

[16]
Title: Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
Subjects: Machine Learning (cs.LG); Statistics Theory (math.ST); Machine Learning (stat.ML)

The developments of Rademacher complexity and PAC-Bayesian theory have been largely independent. One exception is the PAC-Bayes theorem of Kakade, Sridharan, and Tewari (2008), which is established via Rademacher complexity theory by viewing Gibbs classifiers as linear operators. The goal of this paper is to extend this bridge between Rademacher complexity and state-of-the-art PAC-Bayesian theory. We first demonstrate that one can match the fast rate of Catoni's PAC-Bayes bounds (Catoni, 2007) using shifted Rademacher processes (Wegkamp, 2003; Lecu\'{e} and Mitchell, 2012; Zhivotovskiy and Hanneke, 2018). We then derive a new fast-rate PAC-Bayes bound in terms of the "flatness" of the empirical risk surface on which the posterior concentrates. Our analysis establishes a new framework for deriving fast-rate PAC-Bayes bounds and yields new insights on PAC-Bayesian theory.

[17]
Title: Developing Creative AI to Generate Sculptural Objects
Comments: In the Proceedings of International Symposium on Electronic Art (ISEA 2019)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (stat.ML)

We explore the intersection of human and machine creativity by generating sculptural objects through machine learning. This research raises questions about both the technical details of automatic art generation and the interaction between AI and people, as both artists and the audience of art. We introduce two algorithms for generating 3D point clouds and then discuss their actualization as sculpture and incorporation into a holistic art installation. Specifically, the Amalgamated DeepDream (ADD) algorithm solves the sparsity problem caused by the naive DeepDream-inspired approach and generates creative and printable point clouds. The Partitioned DeepDream (PDD) algorithm further allows us to explore more diverse 3D object creation by combining point cloud clustering algorithms and ADD.

[18]
Title: From Text to Sound: A Preliminary Study on Retrieving Sound Effects to Radio Stories
Comments: In the Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019)
Subjects: Information Retrieval (cs.IR); Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)

Sound effects play an essential role in producing high-quality radio stories but require enormous labor cost to add. In this paper, we address the problem of automatically adding sound effects to radio stories with a retrieval-based model. However, directly implementing a tag-based retrieval model leads to high false positives due to the ambiguity of story contents. To solve this problem, we introduce a retrieval-based framework hybridized with a semantic inference model which helps to achieve robust retrieval results. Our model relies on fine-designed features extracted from the context of candidate triggers. We collect two story dubbing datasets through crowdsourcing to analyze the setting of adding sound effects and to train and test our proposed methods. We further discuss the importance of each feature and introduce several heuristic rules for the trade-off between precision and recall. Together with the text-to-speech technology, our results reveal a promising automatic pipeline on producing high-quality radio stories.

[19]
Title: Covert Millimeter-Wave Communication via a Dual-Beam Transmitter
Subjects: Information Theory (cs.IT)

In this paper, we investigate covert communication over millimeter-wave (mmWave) frequencies. In particular, a dual-beam mmWave transmitter, comprised of two independent antenna arrays, attempts to reliably communicate to a receiver Bob when hiding the existence of transmission from a warden Willie. In this regard, operating over mmWave bands not only increases the covertness thanks to directional beams, but also increases the transmission data rates given much more available bandwidths and enables ultra-low form factor transceivers due to the lower wavelengths used compared to the conventional radio frequency (RF) counterpart. We assume that the transmitter Alice employs one of its antenna arrays to form a directive beam for transmission to Bob. The other antenna array is used by Alice to generate another beam toward Willie as a jamming signal with its transmit power changing independently from a transmission block to another block. We characterize Willie's detection performance with the optimal detector and the closed-form of its expected value from Alice's perspective. We further derive the closed-form expression for the outage probability of the Alice-Bob link, which enables characterizing the optimal covert rate that can be achieved using the proposed setup. Our results demonstrate the superiority of mmWave covert communication, in terms of covertness and rate, compared to the RF counterpart.

[20]
Title: Gain More for Less: The Surprising Benefits of QoS Management in Constrained NDN Networks
Journal-ref: Proceedings of ACM ICN 2019
Subjects: Networking and Internet Architecture (cs.NI)

Quality of Service (QoS) in the IP world mainly manages forwarding resources, i.e., link capacities and buffer spaces. In addition, Information Centric Networking (ICN) offers resource dimensions such as in-network caches and forwarding state. In constrained wireless networks, these resources are scarce with a potentially high impact due to lossy radio transmission. In this paper, we explore the two basic service qualities (i) prompt and (ii) reliable traffic forwarding for the case of NDN. The resources we take into account are forwarding and queuing priorities, as well as the utilization of caches and of forwarding state space. We treat QoS resources not only in isolation, but correlate their use on local nodes and between network members. Network-wide coordination is based on simple, predefined QoS code points. Our findings indicate that coordinated QoS management in ICN is more than the sum of its parts and exceeds the impact QoS can have in the IP world.

[21]
Title: Learning document embeddings along with their uncertainties
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)

Majority of the text modelling techniques yield only point estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We present Bayesian subspace multinomial model (Bayesian SMM), a generative log-linear model that learns to represent documents in the form of Gaussian distributions, thereby encoding the uncertainty in its covariance. Additionally, in the proposed Bayesian SMM, we address a commonly encountered problem of intractability that appears during variational inference in mixed-logit models. We also present a generative Gaussian linear classifier for topic identification that exploits the uncertainty in document embeddings. Our intrinsic evaluation using perplexity measure shows that the proposed Bayesian SMM fits the data better as compared to variational auto-encoder based document model. Our topic identification experiments on speech (Fisher) and text (20Newsgroups) corpora show that the proposed Bayesian SMM is robust to over-fitting on unseen test data. The topic ID results show that the proposed model is significantly better than variational auto-encoder based methods and achieve similar results when compared to fully supervised discriminative models.

[22]
Title: Personalizing Search Results Using Hierarchical RNN with Query-aware Attention
Comments: In the Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM 2018)
Subjects: Information Retrieval (cs.IR)

Search results personalization has become an effective way to improve the quality of search engines. Previous studies extracted information such as past clicks, user topical interests, query click entropy and so on to tailor the original ranking. However, few studies have taken into account the sequential information underlying previous queries and sessions. Intuitively, the order of issued queries is important in inferring the real user interests. And more recent sessions should provide more reliable personal signals than older sessions. In addition, the previous search history and user behaviors should influence the personalization of the current query depending on their relatedness. To implement these intuitions, in this paper we employ a hierarchical recurrent neural network to exploit such sequential information and automatically generate user profile from historical data. We propose a query-aware attention model to generate a dynamic user profile based on the input query. Significant improvement is observed in the experiment with data from a commercial search engine when compared with several traditional personalization models. Our analysis reveals that the attention model is able to attribute higher weights to more related past sessions after fine training.

[23]
Title: Implications of Quantum Computing for Artificial Intelligence alignment research
Subjects: Emerging Technologies (cs.ET); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

We introduce a heuristic model of Quantum Computing and apply it to argue that a deep understanding of quantum computing is unlikely to be helpful to address current bottlenecks in Artificial Intelligence Alignment. Our argument relies on the claims that Quantum Computing leads to compute overhang instead of algorithmic overhang, and that the difficulties associated with the measurement of quantum states do not invalidate any major assumptions of current Artificial Intelligence Alignment research agendas. We also discuss tripwiring, adversarial blinding, informed oversight and side effects as possible exceptions.

[24]
Title: Reinforcement Learning is not a Causal problem
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

We use an analogy between non-isomorphic mathematical structures defined over the same set and the algebras induced by associative and causal levels of information in order to argue that Reinforcement Learning, in its current formulation, is not a causal problem, independently if the motivation behind it has to do with an agent taking actions.

[25]
Title: Action recognition with spatial-temporal discriminative filter banks
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Action recognition has seen a dramatic performance improvement in the last few years. Most of the current state-of-the-art literature either aims at improving performance through changes to the backbone CNN network, or they explore different trade-offs between computational efficiency and performance, again through altering the backbone network. However, almost all of these works maintain the same last layers of the network, which simply consist of a global average pooling followed by a fully connected layer. In this work we focus on how to improve the representation capacity of the network, but rather than altering the backbone, we focus on improving the last layers of the network, where changes have low impact in terms of computational cost. In particular, we show that current architectures have poor sensitivity to finer details and we exploit recent advances in the fine-grained recognition literature to improve our model in this aspect. With the proposed approach, we obtain state-of-the-art performance on Kinetics-400 and Something-Something-V1, the two major large-scale action recognition benchmarks.

[26]
Title: P2L: Predicting Transfer Learning for Images and Semantic Relations
Comments: 10 pages, 5 figures, 6 tables
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)

Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately estimate the appropriateness of a previously trained model for use in a new learning task. We use this measure, which we call "Predict To Learn" ("P2L"), in the two very different domains of images and semantic relations, where it predicts, from a set of "source" models, the one model most likely to produce effective transfer for training a given "target" model. We validate our approach thoroughly, by assembling a collection of candidate source models, then fine-tuning each candidate to perform each of a collection of target tasks, and finally measuring how well transfer has been enhanced. Across 95 tasks within multiple domains (images classification and semantic relations), the P2L approach was able to select the best transfer learning model on average, while the heuristic of choosing model trained with the largest data set selected the best model in only 55 cases. These results suggest that P2L captures important information in common between source and target tasks, and that this shared informational structure contributes to successful transfer learning more than simple data size.

[27]
Title: On Object Symmetries and 6D Pose Estimation from Images
Comments: International Conference on 3D Vision
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Objects with symmetries are common in our daily life and in industrial contexts, but are often ignored in the recent literature on 6D pose estimation from images. In this paper, we study in an analytical way the link between the symmetries of a 3D object and its appearance in images. We explain why symmetrical objects can be a challenge when training machine learning algorithms that aim at estimating their 6D pose from images. We propose an efficient and simple solution that relies on the normalization of the pose rotation. Our approach is general and can be used with any 6D pose estimation algorithm. Moreover, our method is also beneficial for objects that are 'almost symmetrical', i.e. objects for which only a detail breaks the symmetry. We validate our approach within a Faster-RCNN framework on a synthetic dataset made with objects from the T-Less dataset, which exhibit various types of symmetries, as well as real sequences from T-Less.

[28]
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR); Machine Learning (stat.ML)

Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic gradient descent (SGD) algorithms for training machine learning models have been proposed. At each step, these algorithms modify the gradients and add noise proportional to the sensitivity of the modified gradients. Under this framework, we propose AdaCliP, a theoretically motivated differentially private SGD algorithm that provably adds less noise compared to the previous methods, by using coordinate-wise adaptive clipping of the gradient. We empirically demonstrate that AdaCliP reduces the amount of added noise and produces models with better accuracy.

[29]
Title: Saccader: Improving Accuracy of Hard Attention Models for Vision
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Machine Learning (stat.ML)

Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, they are often regarded as black boxes. Because they compute a nonlinear function of the entire input image, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is \textit{hard attention}, which selects only relevant portions of the image. However, training hard attention models with only class label supervision is challenging, and hard attention has proved difficult to scale to complex datasets. Here, we propose a novel hard attention model, which we term Saccader, as well as a self-supervised pretraining procedure for this model that does not suffer from optimization challenges. Through pretraining and policy gradient optimization, the Saccader model estimates the relevance of different image patches to the downstream task, and uses a novel cell to select patches to classify at different times. Our approach achieves high accuracy on ImageNet while providing more interpretable predictions.

[30]
Title: Communal Domain Learning for Registration in Drifted Image Spaces
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Designing a registration framework for images that do not share the same probability distribution is a major challenge in modern image analytics yet trivial task for the human visual system (HVS). Discrepancies in probability distributions, also known as \emph{drifts}, can occur due to various reasons including, but not limited to differences in sequences and modalities (e.g., MRI T1-T2 and MRI-CT registration), or acquisition settings (e.g., multisite, inter-subject, or intra-subject registrations). The popular assumption about the working of HVS is that it exploits a communal feature subspace exists between the registering images or fields-of-view that encompasses key drift-invariant features. Mimicking the approach that is potentially adopted by the HVS, herein, we present a representation learning technique of this invariant communal subspace that is shared by registering domains. The proposed communal domain learning (CDL) framework uses a set of hierarchical nonlinear transforms to learn the communal subspace that minimizes the probability differences and maximizes the amount of shared information between the registering domains. Similarity metric and parameter optimization calculations for registration are subsequently performed in the drift-minimized learned communal subspace. This generic registration framework is applied to register multisequence (MR: T1, T2) and multimodal (MR, CT) images. Results demonstrated generic applicability, consistent performance, and statistically significant improvement for both multi-sequence and multi-modal data using the proposed approach ($p$-value$<0.001$; Wilcoxon rank sum test) over baseline methods.

[31]
Title: Line and Plane Cover Numbers Revisited
Comments: Appears in the Proceedings of the 27th International Symposium on Graph Drawing and Network Visualization (GD 2019)
Subjects: Computational Geometry (cs.CG); Discrete Mathematics (cs.DM)

A measure for the visual complexity of a straight-line crossing-free drawing of a graph is the minimum number of lines needed to cover all vertices. For a given graph $G$, the minimum such number (over all drawings in dimension $d \in \{2,3\}$) is called the \emph{$d$-dimensional weak line cover number} and denoted by $\pi^1_d(G)$. In 3D, the minimum number of \emph{planes} needed to cover all vertices of~$G$ is denoted by $\pi^2_3(G)$. When edges are also required to be covered, the corresponding numbers $\rho^1_d(G)$ and $\rho^2_3(G)$ are called the \emph{(strong) line cover number} and the \emph{(strong) plane cover number}.
Computing any of these cover numbers -- except $\pi^1_2(G)$ -- is known to be NP-hard. The complexity of computing $\pi^1_2(G)$ was posed as an open problem by Chaplick et al. [WADS 2017]. We show that it is NP-hard to decide, for a given planar graph~$G$, whether $\pi^1_2(G)=2$. We further show that the universal stacked triangulation of depth~$d$, $G_d$, has $\pi^1_2(G_d)=d+1$. Concerning~3D, we show that any $n$-vertex graph~$G$ with $\rho^2_3(G)=2$ has at most $5n-19$ edges, which is tight.

[32]
Title: An Expert System Approach for determine the stage of UiTM Perlis Palapes Cadet Performance and Ranking Selection
Journal-ref: Journal of Computer Science & Computational Mathematics (2012)
Subjects: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

The palapes cadets are one of the uniform organizations in UiTM Perlis for extra-curricular activities. The palapes cadets arrange their organization in a hierarchy according to grade. Senior uniform officer (SUO) is the highest rank, followed by a junior uniform officer (JUO), sergeant, corporal, lance corporal, and lastly, cadet officer, which is the lowest rank. The palapes organization has several methods to measure performance toward promotion to a higher rank, whether individual performance or in a group. Cadets are selected for promotion based on demonstrated leadership abilities, acquired skills, physical fitness, and comprehension of information as measured through standardized testing. However, this method is too complicated when manually assessed by a trainer or coach. Therefore, this study will propose an expert system, which is one of the artificial intelligence techniques that can recognize the readiness and progression of a palapes cadet.

[33]
Title: Understanding and Partitioning Mobile Traffic using Internet Activity Records Data -- A Spatiotemporal Approach
Comments: 2019 28th Wireless and Optical Communications Conference (WOCC)
Subjects: Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG); Signal Processing (eess.SP); Machine Learning (stat.ML)

The internet activity records (IARs) of a mobile cellular network posses significant information which can be exploited to identify the network's efficacy and the mobile users' behavior. In this work, we extract useful information from the IAR data and identify a healthy predictability of spatio-temporal pattern within the network traffic. The information extracted is helpful for network operators to plan effective network configuration and perform management and optimization of network's resources. We report experimentation on spatiotemporal analysis of IAR data of the Telecom Italia. Based on this, we present mobile traffic partitioning scheme. Experimental results of the proposed model is helpful in modelling and partitioning of network traffic patterns.

[34]
Title: FusionNet: Incorporating Shape and Texture for Abnormality Detection in 3D Abdominal CT Scans
Comments: Accepted to MICCAI 2019 Workshop(MLMI)(8 pages, 3 figures)
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Automatic abnormality detection in abdominal CT scans can help doctors improve the accuracy and efficiency in diagnosis. In this paper we aim at detecting pancreatic ductal adenocarcinoma (PDAC), the most common pancreatic cancer. Taking the fact that the existence of tumor can affect both the shape and the texture of pancreas, we design a system to extract the shape and texture feature at the same time for detecting PDAC. In this paper we propose a two-stage method for this 3D classification task. First, we segment the pancreas into a binary mask. Second, a FusionNet is proposed to take both the binary mask and CT image as input and perform a binary classification. The optimal architecture of the FusionNet is obtained by searching a pre-defined functional space. We show that the classification results using either shape or texture information are complementary, and by fusing them with the optimized architecture, the performance improves by a large margin. Our method achieves a specificity of 97% and a sensitivity of 92% on 200 normal scans and 136 scans with PDAC.

[35]
Title: Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR); Machine Learning (stat.ML)

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. In this paper, we present MODEF, a cross-layer model diversity ensemble framework. MODEF intelligently combines unsupervised model denoising ensemble with supervised model verification ensemble by quantifying model diversity, aiming to boost the robustness of the target model against adversarial examples. Evaluated using eleven representative attacks on popular benchmark datasets, we show that MODEF achieves remarkable defense success rates, compared with existing defense methods, and provides a superior capability of repairing adversarial inputs and making correct predictions with high accuracy in the presence of black-box attacks.

[36]
Title: Existence and hardness of conveyor belts
Subjects: Computational Geometry (cs.CG); Combinatorics (math.CO)

An open problem of Manuel Abellanas asks whether every set of disjoint closed unit disks in the plane can be connected by a conveyor belt, which means a tight simple closed curve that touches the boundary of each disk, possibly multiple times. We prove three main results. First, for unit disks whose centers are both $x$-monotone and $y$-monotone, or whose centers have $x$-coordinates that differ by at least two units, a conveyor belt always exists and can be found efficiently. Second, it is NP-complete to determine whether disks of varying radii have a conveyor belt, and it remains NP-complete when we constrain the belt to touch disks exactly once. Third, any disjoint set of $n$ disks of arbitrary radii can be augmented by $O(n)$ "guide" disks so that the augmented system has a conveyor belt touching each disk exactly once, answering a conjecture of Demaine, Demaine, and Palop.

[37]
Title: Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation
Journal-ref: 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Weakly-supervised learning under image-level labels supervision has been widely applied to semantic segmentation of medical lesions regions. However, 1) most existing models rely on effective constraints to explore the internal representation of lesions, which only produces inaccurate and coarse lesions regions; 2) they ignore the strong probabilistic dependencies between target lesions dataset (e.g., enteroscopy images) and well-to-annotated source diseases dataset (e.g., gastroscope images). To better utilize these dependencies, we present a new semantic lesions representation transfer model for weakly-supervised endoscopic lesions segmentation, which can exploit useful knowledge from relevant fully-labeled diseases segmentation task to enhance the performance of target weakly-labeled lesions segmentation task. More specifically, a pseudo label generator is proposed to leverage seed information to generate highly-confident pseudo pixel labels by incorporating class balance and super-pixel spatial prior. It can iteratively include more hard-to-transfer samples from weakly-labeled target dataset into training set. Afterwards, dynamically searched feature centroids for same class among different datasets are aligned by accumulating previously-learned features. Meanwhile, adversarial learning is also employed in this paper, to narrow the gap between the lesions among different datasets in output space. Finally, we build a new medical endoscopic dataset with 3659 images collected from more than 1100 volunteers. Extensive experiments on our collected dataset and several benchmark datasets validate the effectiveness of our model.

[38]
Title: Learning Joint Embedding for Cross-Modal Retrieval
Authors: Donghuo Zeng
Comments: 3 pages, 1 figure, Submitted to ICDM2019 Ph.D. Forum session
Subjects: Information Retrieval (cs.IR); Multimedia (cs.MM)

A cross-modal retrieval process is to use a query in one modality to obtain relevant data in another modality. The challenging issue of cross-modal retrieval lies in bridging the heterogeneous gap for similarity computation, which has been broadly discussed in image-text, audio-text, and video-text cross-modal multimedia data mining and retrieval. However, the gap in temporal structures of different data modalities is not well addressed due to the lack of alignment relationship between temporal cross-modal structures. Our research focuses on learning the correlation between different modalities for the task of cross-modal retrieval. We have proposed an architecture: Supervised-Deep Canonical Correlation Analysis (S-DCCA), for cross-modal retrieval. In this forum paper, we will talk about how to exploit triplet neural networks (TNN) to enhance the correlation learning for cross-modal retrieval. The experimental result shows the proposed TNN-based supervised correlation learning architecture can get the best result when the data representation extracted by supervised learning.

[39]
Title: Asymmetric Non-local Neural Networks for Semantic Segmentation
Comments: To appear in ICCV 2019
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic segmentation, which has two prominent components: Asymmetric Pyramid Non-local Block (APNB) and Asymmetric Fusion Non-local Block (AFNB). APNB leverages a pyramid sampling module into the non-local block to largely reduce the computation and memory consumption without sacrificing the performance. AFNB is adapted from APNB to fuse the features of different levels under a sufficient consideration of long range dependencies and thus considerably improves the performance. Extensive experiments on semantic segmentation benchmarks demonstrate the effectiveness and efficiency of our work. In particular, we report the state-of-the-art performance of 81.3 mIoU on the Cityscapes test set. For a 256x128 input, APNB is around 6 times faster than a non-local block on GPU while 28 times smaller in GPU running memory occupation. Code is available at: https://github.com/MendelXu/ANN.git.

[40]
Title: Differentiated context-aware hook placement for different owners' smartphones
Subjects: Software Engineering (cs.SE)

A hook is a piece of code. It checks user privacy policy before some sensitive operations happen. We propose an automated solution named Prihook for hook placement in the Android Framework. Addressing specific context-aware user privacy concerns, the hook placement in Prihook is personalized. Specifically, we design User Privacy Preference Table (UPPT) to help a user express his privacy concerns. And we leverage machine learning to discover a Potential Method Set (consisting of Sensor Data Access Methods and Sensor Control Methods) from which we can select a particular subset to put hooks. We propose a mapping from words in the UPPT lexicon to methods in the Potential Method Set. With this mapping, Prihook is able to (a) select a specific set of methods; and (b) generate and place hooks automatically. We test Prihook separately on 6 typical UPPTs representing 6 kinds of resource-sensitive UPPTs, and no user privacy violation is found. The experimental results show that the hooks placed by PriHook have small runtime overhead.

[41]
Title: Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation
Comments: Accepted by ACM Multimedia(ACM MM) 2019
Subjects: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)

In this paper, we investigate the problem of unpaired video-to-video translation. Given a video in the source domain, we aim to learn the conditional distribution of the corresponding video in the target domain, without seeing any pairs of corresponding videos. While significant progress has been made in the unpaired translation of images, directly applying these methods to an input video leads to low visual quality due to the additional time dimension. In particular, previous methods suffer from semantic inconsistency (i.e., semantic label flipping) and temporal flickering artifacts. To alleviate these issues, we propose a new framework that is composed of carefully-designed generators and discriminators, coupled with two core objective functions: 1) content preserving loss and 2) temporal consistency loss. Extensive qualitative and quantitative evaluations demonstrate the superior performance of the proposed method against previous approaches. We further apply our framework to a domain adaptation task and achieve favorable results.

[42]
Title: MoEL: Mixture of Empathetic Listeners
Subjects: Computation and Language (cs.CL)

Previous research on empathetic dialogue systems has mostly focused on generating responses given certain emotions. However, being empathetic not only requires the ability of generating emotional responses, but more importantly, requires the understanding of user emotions and replying appropriately. In this paper, we propose a novel end-to-end approach for modeling empathy in dialogue systems: Mixture of Empathetic Listeners (MoEL). Our model first captures the user emotions and outputs an emotion distribution. Based on this, MoEL will softly combine the output states of the appropriate Listener(s), which are each optimized to react to certain emotions, and generate an empathetic response. Human evaluations on empathetic-dialogues (Rashkin et al., 2018) dataset confirm that MoEL outperforms multitask training baseline in terms of empathy, relevance, and fluency. Furthermore, the case study on generated responses of different Listeners shows high interpretability of our model.

[43]
Title: Improving Neural Machine Translation with Pre-trained Representation
Subjects: Computation and Language (cs.CL)

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or extracting information from word embedding. In contrast, the power of sentence-level contextual knowledge which is more complex and diverse, playing an important role in natural language generation, has not been fully exploited. In this paper, we propose a novel structure which could leverage monolingual data to acquire sentence-level contextual representations. Then, we design a framework for integrating both source and target sentence-level representations into NMT model to improve the translation quality. Experimental results on Chinese-English, German-English machine translation tasks show that our proposed model achieves improvement over strong Transformer baselines, while experiments on English-Turkish further demonstrate the effectiveness of our approach in the low-resource scenario.

[44]
Title: A false data injection attack method for generator dynamic state estimation
Comments: in Chinese, Accepted by Transactions of China Electrotechnical Society
Subjects: Systems and Control (eess.SY); Signal Processing (eess.SP)

Accurate and reliable dynamic state quantities of generators are very important for real-time monitoring and control of the power system. The emergence of cyber attacks has brought new challenges to the state estimation of generators. Especially, false data injection (FDI) attacks deteriorate the accuracy of state estimation by injecting the false data into the measurement device. In this regard, this paper proposes for the first time an FDI attack model based on the dynamic state estimation of generators. Firstly, Taylor's formula was used to linearize the generator's measurement equation. Secondly, according to the principle that the measurement residuals before and after the FDI attack are equal, the expressions of the attack vectors were established, and they were applied to the measurement quantities to avoid the conventional bad data detection. Thereby, the FDI attacks were successfully implemented. Then, three attack scenarios were set according to the degree of the FDI attacks, and they were tested by the cubature Kalman filter (CKF) and the robust cubature Kalman filter (RCKF). Finally, the simulation results of the IEEE 9-bus system and the New England 16-machine 68-bus system verify the effectiveness of the proposed FDI attacks.

[45]
Title: Latent Relation Language Models
Subjects: Computation and Language (cs.CL)

In this paper, we propose Latent Relation Language Models (LRLMs), a class of language models that parameterizes the joint distribution over the words in a document and the entities that occur therein via knowledge graph relations. This model has a number of attractive properties: it not only improves language modeling performance, but is also able to annotate the posterior probability of entity spans for a given text through relations. Experiments demonstrate empirical improvements over both a word-based baseline language model and a previous approach that incorporates knowledge graph information. Qualitative analysis further demonstrates the proposed model's ability to learn to predict appropriate relations in context.

[46]
Title: Detection-averse optimal and receding-horizon control for Markov decision processes
Subjects: Systems and Control (eess.SY); Optimization and Control (math.OC)

In this paper, we consider a Markov decision process (MDP), where the ego agent has a nominal objective to pursue while needs to hide its state from detection by an adversary. After formulating the problem, we first propose a value iteration (VI) approach to solve it. To overcome the "curse of dimensionality" and thus gain scalability to larger-sized problems, we then propose a receding-horizon optimization (RHO) approach to obtain approximate solutions. We use examples to illustrate and compare the VI and RHO approaches, and to show the potential of our problem formulation for practical applications.

[47]
Title: A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component
Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG)

Recently, deep learning, which uses Deep Neural Networks (DNN), plays an important role in many fields. A secure neural network model with a secure training/inference scheme is indispensable to many applications. To accomplish such a task usually needs one of the entities (the customer or the service provider) to provide private information (customer's data or the model) to the other. Without a secure scheme and the mutual trust between the service providers and their customers, it will be an impossible mission. In this paper, we propose a novel privacy-preserving deep learning model and a secure training/inference scheme to protect the input, the output, and the model in the application of the neural network. We utilize the innate properties of a deep neural network to design a secure mechanism without using any complicated cryptography component. The security analysis shows our proposed scheme is secure and the experimental results also demonstrate that our method is very efficient and suitable for real applications.

[48]
Title: Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking
Subjects: Computation and Language (cs.CL)

Dialogue state tracking (DST) is an essential component in task-oriented dialogue systems, which estimates user goals at every dialogue turn. However, most previous approaches usually suffer from the following problems. Many discriminative models, especially end-to-end (E2E) models, are difficult to extract unknown values that are not in the candidate ontology; previous generative models, which can extract unknown values from utterances, degrade the performance due to ignoring the semantic information of pre-defined ontology. Besides, previous generative models usually need a hand-crafted list to normalize the generated values. How to integrate the semantic information of pre-defined ontology and dialogue text (heterogeneous texts) to generate unknown values and improve performance becomes a severe challenge. In this paper, we propose a Copy-Enhanced Heterogeneous Information Learning model with multiple encoder-decoder for DST (CEDST), which can effectively generate all possible values including unknown values by copying values from heterogeneous texts. Meanwhile, CEDST can effectively decompose the large state space into several small state spaces through multi-encoder, and employ multi-decoder to make full use of the reduced spaces to generate values. Multi-encoder-decoder architecture can significantly improve performance. Experiments show that CEDST can achieve state-of-the-art results on two datasets and our constructed datasets with many unknown values.

[49]
Title: Pilot Study on Verifying the Monotonic Relationship between Error and Uncertainty in Deformable Registration for Neurosurgery
Subjects: Computer Vision and Pattern Recognition (cs.CV)

In image-guided neurosurgery, deformable registration currently is not a clinical routine. Although using it in practice is a goal for image-guided therapy, this goal is hampered because surgeons are wary of the less predictable deformable registration error. In the preoperative- to-intraoperative registration, when surgeons notice a misaligned image pattern, they want to know whether it is a registration error or an actual deformation caused by tumor resection or retraction. Here, surgeons need a spatial distribution of error to help them make a better-informed decision, i.e., ignore locations with high error. However, such an error estimate is difficult to acquire. Alternatively, probabilistic image registration (PIR) methods give measures of registration uncertainty, which is a potential surrogate for assessing the quality of registration results. It is intuitive and believed by a lot of people that high uncertainty indicates a large error. Yet to the best of our knowledge, no such conclusion has been reported in the PIR literature. In this study, we look at one PIR method and give preliminary results showing that point-wise registration error and uncertainty are monotonically correlated.

[50]
Title: A sufficient condition for a linear speedup in competitive parallel computing
Authors: Naoki Yonezawa
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC)

In competitive parallel computing, the identical copies of a code in a phase of a sequential program are assigned to processor cores and the result of the fastest core is adopted. In the literature, it is reported that a superlinear speedup can be achieved if there is an enough fluctuation among the execution times consumed by the cores. Competitive parallel computing is a promising approach to use a huge amount of cores effectively. However, there is few theoretical studies on speedups which can be achieved by competitive parallel computing at present. In this paper, we present a behavioral model of competitive parallel computing and provide a means to predict a speedup which competitive parallel computing yields through theoretical analyses and simulations. We also found a sufficient condition to provide a linear speedup which competitive parallel computing yields. More specifically, it is sufficient for the execution times which consumed by the cores to follow an exponential distribution. In addition, we found that the different distributions which have the identical coefficient of variation (CV) do not always provide the identical speedup. While CV is a convenient measure to predict a speedup, it is not enough to provide an exact prediction.

[51]
Title: Fine-tuning BERT for Joint Entity and Relation Extraction in Chinese Medical Text
Comments: 8 pages, 2 figures, submitted to BIBM 2019
Subjects: Computation and Language (cs.CL)

Entity and relation extraction is the necessary step in structuring medical text. However, the feature extraction ability of the bidirectional long short term memory network in the existing model does not achieve the best effect. At the same time, the language model has achieved excellent results in more and more natural language processing tasks. In this paper, we present a focused attention model for the joint entity and relation extraction task. Our model integrates well-known BERT language model into joint learning through dynamic range attention mechanism, thus improving the feature representation ability of shared parameter layer. Experimental results on coronary angiography texts collected from Shuguang Hospital show that the F1-score of named entity recognition and relation classification tasks reach 96.89% and 88.51%, which are better than state-of-the-art methods 1.65% and 1.22%, respectively.

[52]
Title: Improved Cardinality Estimation by Learning Queries Containment Rates
Subjects: Databases (cs.DB); Machine Learning (cs.LG)

The containment rate of query Q1 in query Q2 over database D is the percentage of Q1's result tuples over D that are also in Q2's result over D. We directly estimate containment rates between pairs of queries over a specific database. For this, we use a specialized deep learning scheme, CRN, which is tailored to representing pairs of SQL queries. Result-cardinality estimation is a core component of query optimization. We describe a novel approach for estimating queries result-cardinalities using estimated containment rates among queries. This containment rate estimation may rely on CRN or embed, unchanged, known cardinality estimation methods. Experimentally, our novel approach for estimating cardinalities, using containment rates between queries, on a challenging real-world database, realizes significant improvements to state of the art cardinality estimation methods.

[53]
Title: Restricted Recurrent Neural Networks
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)

Recurrent Neural Network (RNN) and its variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), have become standard building blocks for learning online data of sequential nature in many research areas, including natural language processing and speech data analysis. In this paper, we present a new methodology to significantly reduce the number of parameters in RNNs while maintaining performance that is comparable or even better than classical RNNs. The new proposal, referred to as Restricted Recurrent Neural Network (RRNN), restricts the weight matrices corresponding to the input data and hidden states at each time step to share a large proportion of parameters. The new architecture can be regarded as a compression of its classical counterpart, but it does not require pre-training or sophisticated parameter fine-tuning, both of which are major issues in most existing compression techniques. Experiments on natural language modeling show that compared with its classical counterpart, the restricted recurrent architecture generally produces comparable results at about 50% compression rate. In particular, the Restricted LSTM can outperform classical RNN with even less number of parameters.

[54]
Title: Data-driven model reduction, Wiener projections, and the Mori-Zwanzig formalism
Authors: Kevin K. Lin, Fei Lu
Subjects: Numerical Analysis (math.NA); Computational Physics (physics.comp-ph); Machine Learning (stat.ML)

First-principles models of complex dynamic phenomena often have many degrees of freedom, only a small fraction of which may be scientifically relevant or observable. Reduced models distill such phenomena to their essence by modeling only relevant variables, thus decreasing computational cost and clarifying dynamical mechanisms. Here, we consider data-driven model reduction for nonlinear dynamical systems without sharp scale separation. Motivated by a discrete-time version of the Mori-Zwanzig projection operator formalism and the Wiener filter, we propose a simple and flexible mathematical formulation based on Wiener projection, which decomposes a nonlinear dynamical system into a component predictable by past values of relevant variables and its orthogonal complement. Wiener projection is equally applicable to deterministic chaotic dynamics and randomly-forced systems, and provides a natural starting point for systematic approximations. In particular, we use it to derive NARMAX models from an underlying dynamical system, thereby clarifying the scope of these widely-used tools in time series analysis. We illustrate its versatility on the Kuramoto-Sivashinsky model of spatiotemporal chaos and a stochastic Burgers equation.

[55]
Title: Eliminating Impulsive Noise in Pilot-Aided OFDM Channels via Dual of Penalized Atomic Norm
Subjects: Information Theory (cs.IT); Signal Processing (eess.SP)

In this paper, we propose a novel estimator for pilot-aided orthogonal frequency division multiplexing (OFDM) channels in an additive Gaussian and impulsive perturbation environment. Due to sensor failure which might happen because of man-made noise, a number of measurements in high rate communication systems is often corrupted by impulsive noise. High power impulsive noise is generally an obstacle for OFDM systems as valuable information will be completely lost. To overcome this concern, an objective function based on a penalized atomic norm minimization (PANM) is provided in order to promote the sparsity of time dispersive channels and impulsive noise. The corresponding dual problem of the PANM is then converted to tractable semidefinite programming. It has shown that one can simultaneously estimate the time dispersive channels in a continuous dictionary and the location of impulsive noise using the dual problem. Several numerical experiments are carried out to evaluate the performance of the proposed estimator.

[56]
Title: KeystoneDepth: Visualizing History in 3D
Subjects: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)

This paper introduces the largest and most diverse collection of rectified stereo image pairs to the research community, KeystoneDepth, consisting of tens of thousands of stereographs of historical people, events, objects, and scenes between 1860 and 1963. Leveraging the Keystone-Mast raw scans from the California Museum of Photography, we apply multiple processing steps to produce clean stereo image pairs, complete with calibration data, rectification transforms, and depthmaps. A second contribution is a novel approach for view synthesis that runs at real-time rates on a mobile device, simulating the experience of looking through an open window into these historical scenes. We produce results for thousands of antique stereographs, capturing many important historical moments.

[57]
Title: User Diverse Preference Modeling by Multimodal Attentive Metric Learning
Comments: Accepted by ACM Multimedia 2019 as a full paper
Subjects: Information Retrieval (cs.IR); Multimedia (cs.MM)

Most existing recommender systems represent a user's preference with a feature vector, which is assumed to be fixed when predicting this user's preferences for different items. However, the same vector cannot accurately capture a user's varying preferences on all items, especially when considering the diverse characteristics of various items. To tackle this problem, in this paper, we propose a novel Multimodal Attentive Metric Learning (MAML) method to model user diverse preferences for various items. In particular, for each user-item pair, we propose an attention neural network, which exploits the item's multimodal features to estimate the user's special attention to different aspects of this item. The obtained attention is then integrated into a metric-based learning method to predict the user preference on this item. The advantage of metric learning is that it can naturally overcome the problem of dot product similarity, which is adopted by matrix factorization (MF) based recommendation models but does not satisfy the triangle inequality property. In addition, it is worth mentioning that the attention mechanism cannot only help model user's diverse preferences towards different items, but also overcome the geometrically restrictive problem caused by collaborative metric learning. Extensive experiments on large-scale real-world datasets show that our model can substantially outperform the state-of-the-art baselines, demonstrating the potential of modeling user diverse preference for recommendation.

[58]
Title: On the Robustness of Unsupervised and Semi-supervised Cross-lingual Word Embedding Learning
Comments: 13 pages, 2 figures, 7 tables
Subjects: Computation and Language (cs.CL)

Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings by aligning monolingual spaces have shown that accurate alignments can be obtained with little or no supervision. However, the focus has been on a particular controlled scenario for evaluation, and there is no strong evidence on how current state-of-the-art systems would fare with noisy text or for language pairs with major linguistic differences. In this paper we present an extensive evaluation over multiple cross-lingual embedding models, analyzing their strengths and limitations with respect to different variables such as target language, training corpora and amount of supervision. Our conclusions put in doubt the view that high-quality cross-lingual embeddings can always be learned without much supervision.

[59]
Title: RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to fully explore their corresponding full-precision models, causing a significant performance gap between them. In this paper, we propose rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework. In particular, we use a GAN to train the 1-bit binary network with the guidance of its corresponding full-precision model, which significantly improves the performance of BCNNs. The rectified convolutional layers are generic and flexible, and can be easily incorporated into existing DCNNs such as WideResNets and ResNets. Extensive experiments demonstrate the superior performance of the proposed RBCNs over state-of-the-art BCNNs. In particular, our method shows strong generalization on the object tracking task.

[60]
Title: Boosting the Rating Prediction with Click Data and Textual Contents
Subjects: Information Retrieval (cs.IR); Machine Learning (cs.LG)

Matrix factorization (MF) is one of the most efficient methods for rating predictions. MF learns user and item representations by factorizing the user-item rating matrix. Further, textual contents are integrated to conventional MF to address the cold-start problem. However, the textual contents do not reflect all aspects of the items. In this paper, we propose a model that leverages the information hidden in the item co-click (i.e., items that are often clicked together by a user) into learning item representations. We develop TCMF (Textual Co Matrix Factorization) that learns the user and item representations jointly from the user-item matrix, textual contents and item co-click matrix built from click data. Item co-click information captures the relationships between items which are not captured via textual contents. The experiments on two real-world datasets MovieTweetings, and Bookcrossing) demonstrate that our method outperforms competing methods in terms of rating prediction. Further, we show that the proposed model can learn effective item representations by comparing with state-of-the-art methods in classification task which uses the item representations as input vectors.

[61]
Title: A Realistic Face-to-Face Conversation System based on Deep Neural Networks
Comments: Accepted to ICCV 2019 workshop
Subjects: Computer Vision and Pattern Recognition (cs.CV); Sound (cs.SD); Audio and Speech Processing (eess.AS); Image and Video Processing (eess.IV)

To improve the experiences of face-to-face conversation with avatar, this paper presents a novel conversation system. It is composed of two sequence-to-sequence models respectively for listening and speaking and a Generative Adversarial Network (GAN) based realistic avatar synthesizer. The models exploit the facial action and head pose to learn natural human reactions. Based on the models' output, the synthesizer uses the Pixel2Pixel model to generate realistic facial images. To show the improvement of our system, we use a 3D model based avatar driving scheme as a reference. We train and evaluate our neural networks with the data from ESPN shows. Experimental results show that our conversation system can generate natural facial reactions and realistic facial images.

[62]
Title: Towards a Structural Framework for Explicit Domain Knowledge in Visual Analytics
Authors: Alexander Rind, Markus Wagner, Wolfgang Aigner (St. Poelten University of Applied Sciences, Austria)
Subjects: Human-Computer Interaction (cs.HC)

Clinicians and other analysts working with healthcare data are in need for better support to cope with large and complex data. While an increasing number of visual analytics environments integrates explicit domain knowledge as a means to deliver a precise representation of the available data, theoretical work so far has focused on the role of knowledge in the visual analytics process. There has been little discussion about how such explicit domain knowledge can be structured in a generalized framework. This paper collects desiderata for such a structural framework, proposes how to address these desiderata based on the model of linked data, and demonstrates the applicability in a visual analytics environment for physiotherapy.

[63]
Title: GeoBlocks: A Query-Driven Storage Layout for Geospatial Data
Authors: Christian Winter (1), Andreas Kipf (1), Thomas Neumann (1), Alfons Kemper (1) ((1) Technical University of Munich)
Subjects: Databases (cs.DB)

City authorities need to analyze urban geospatial data to improve transportation and infrastructure. Current tools do not address the exploratory and interactive nature of these analyses and in many cases consult the raw data to compute query results. While pre-aggregation and materializing intermediate query results is common practice in many OLAP settings, it is rarely used to speed up geospatial queries. We introduce GeoBlocks, a pre-aggregating, query-driven storage layout for geospatial point data that can provide approximate, yet precision-bounded aggregation results over arbitrary query polygons. GeoBlocks adapt to the skew naturally present in query workloads to improve query performance over time. In summary, GeoBlocks outperform on-the-fly aggregation by up to several orders of magnitude, providing the sub-second query latencies required for interactive analytics.

[64]
Title: Predict Emoji Combination with Retrieval Strategy
Comments: 4 pages, 2 figures, published in anlp.jp 2019
Subjects: Computation and Language (cs.CL)

As emojis are widely used in social media, people not only use an emoji to express their emotions or mention things but also extend its usage to represent complicate emotions, concepts or activities by combining multiple emojis. In this work, we study how emoji combination, a consecutive emoji sequence, is used like a new language. We propose a novel algorithm called Retrieval Strategy to predict what emoji combination follows given a short text as context. Our algorithm treats emoji combinations as phrase in language, ranking sets of emoji combinations like retrieving words from dictionary. We show that our algorithm largely improves the F1 score from 0.141 to 0.204 on emoji combination prediction task.

[65]
Title: Video-based Bottleneck Detection utilizing Lagrangian Dynamics in Crowded Scenes
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Avoiding bottleneck situations in crowds is critical for the safety and comfort of people at large events or in public transportation. Based on the work of Lagrangian motion analysis we propose a novel video-based bottleneckdetector by identifying characteristic stowage patterns in crowd-movements captured by optical flow fields. The Lagrangian framework allows to assess complex timedependent crowd-motion dynamics at large temporal scales near the bottleneck by two dimensional Lagrangian fields. In particular we propose long-term temporal filtered Finite Time Lyapunov Exponents (FTLE) fields that provide towards a more global segmentation of the crowd movements and allows to capture its deformations when a crowd is passing a bottleneck. Finally, these deformations are used for an automatic spatio-temporal detection of such situations. The performance of the proposed approach is shown in extensive evaluations on the existing J\"ulich and AGORASET datasets, that we have updated with ground truth data for spatio-temporal bottleneck analysis.

[66]
Title: Mobility in the Sky: Performance and Mobility Analysis for Cellular-Connected UAVs
Subjects: Information Theory (cs.IT); Signal Processing (eess.SP)

Providing connectivity to unmanned aerial vehicle-user equipments such as drones or flying taxis is a major challenge for tomorrow cellular systems. In this paper, the use of coordinated multi-point transmission for providing seamless connectivity to UAV user equipments is investigated. In particular, a network of clustered ground base stations that cooperatively serve a number of UAVUEs is considered. Two scenarios are studied: scenarios with static, hovering UAV user equipments and scenarios with mobile UAV-UEs. Under a maximum ratio transmission, a novel framework is developed and leveraged to derive upper and lower bounds on the UAV-UE coverage probability for both scenarios. Using the derived results, the effects of various system parameters such as collaboration distance, UAVUE altitude, and UAV-UE velocity on the achievable performance are studied. Results reveal that, for both static and mobile UAV user equipments, when the BS antennas are tilted downwards, the coverage probability of a high-altitude UAV-UE is upper bounded by that of ground users regardless of the transmission scheme. Moreover, for low signal-to-interference-ratio thresholds, it is shown that CoMP transmission can improve the coverage probability of UAV user equipments, e.g., from 28% under the nearest association scheme to 60% for a collaboration distance of 200m.

[67]
Title: Free Theorems Simply, via Dinaturality
Comments: Part of DECLARE 19 proceedings
Subjects: Programming Languages (cs.PL)

Free theorems are a popular tool in reasoning about parametrically polymorphic code. They are also of instructive use in teaching. Their derivation, though, can be tedious, as it involves unfolding a lot of definitions, then hoping to be able to simplify the resulting logical formula to something nice and short. Even in a mechanised generator it is not easy to get the right heuristics in place to achieve good outcomes. Dinaturality is a categorical abstraction that captures many instances of free theorems. Arguably, its origins are more conceptually involved to explain, though, and generating useful statements from it also has its pitfalls. We present a simple approach for obtaining dinaturality-related free theorems from the standard formulation of relational parametricity in a rather direct way. It is conceptually appealing and easy to control and implement, as the provided Haskell code shows.

[68]
Title: Decentralized Federated Learning: A Segmented Gossip Approach
Comments: Accepted to the 1st International Workshop on Federated Machine Learning for User Privacy and Data Confidentiality (FML'19)
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Networking and Internet Architecture (cs.NI); Machine Learning (stat.ML)

The emerging concern about data privacy and security has motivated the proposal of federated learning, which allows nodes to only synchronize the locally-trained models instead their own original data. Conventional federated learning architecture, inherited from the parameter server design, relies on highly centralized topologies and the assumption of large nodes-to-server bandwidths. However, in real-world federated learning scenarios the network capacities between nodes are highly uniformly distributed and smaller than that in a datacenter. It is of great challenges for conventional federated learning approaches to efficiently utilize network capacities between nodes. In this paper, we propose a model segment level decentralized federated learning to tackle this problem. In particular, we propose a segmented gossip approach, which not only makes full utilization of node-to-node bandwidth, but also has good training convergence. The experimental results show that even the training time can be highly reduced as compared to centralized federated learning.

[69]
Title: Leveraging creativity in requirements elicitation within agile software development: a systematic literature review
Subjects: Software Engineering (cs.SE)

Agile approaches tend to focus solely on scoping and simplicity rather than on problem solving and discovery. This hampers the development of innovative solutions. Additionally, little has been said about how to capture and represent the real user needs. To fill this gap, some authors argue in favor of the application of Creative thinking for requirements elicitation within agile software development. This synergy between creativeness and agility has arisen as a new means of bringing innovation and flexibility to increasingly demanding software. The aim of the present study is therefore to employ a systematic review to investigate the state-of-the-art of those approaches that leverage creativity in requirements elicitation within Agile Software Development, as well as the benefits, limitations and strength of evidence of these approaches. The search strategy identified 1451 studies. The selected studies contained 13 different and unique proposals. These approaches provide evidence that enhanced creativity in requirements elicitation can be successfully implemented in real software projects. We specifically observed that projects related to user interface development, such as those for mobile or web applications, are good candidates for the use of these approaches. We have also found that agile methodologies are preferred when introducing creativity into requirements elicitation. Despite this being a new research field, there is a mixture of techniques, tools and processes that have already been and are currently being successfully tested in industry. Finally, we have found that, although creativity is an important ingredient with which to bring about innovation, it is not always sufficient to generate new requirements because this needs to be followed by user engagement and a specific context in which proper conditions, such as flexibility, time or resources, have to be met.

[70]
Title: Technical Report on Implementing Ranking-Based Semantics in ConArg
Comments: 10 pages, 10 figures, 4 tables
Subjects: Artificial Intelligence (cs.AI)

ConArg is a suite of tools that offers a wide series of applications for dealing with argumentation problems. In this work, we present the advances we made in implementing a ranking-based semantics, based on computational choice power indexes, within ConArg. Such kind of semantics represents a method for sorting the arguments of an abstract argumentation framework, according to some preference relation. The ranking-based semantics we implement relies on Shapley, Banzhaf, Deegan-Packel and Johnston power index, transferring well know properties from computational social choice to argumentation framework ranking-based semantics.

[71]
Subjects: Social and Information Networks (cs.SI)

[72]
Title: A Quality Metric for Visualization of Clusters in Graphs
Comments: Appears in the Proceedings of the 27th International Symposium on Graph Drawing and Network Visualization (GD 2019)
Subjects: Data Structures and Algorithms (cs.DS); Human-Computer Interaction (cs.HC); Social and Information Networks (cs.SI)

Traditionally, graph quality metrics focus on readability, but recent studies show the need for metrics which are more specific to the discovery of patterns in graphs. Cluster analysis is a popular task within graph analysis, yet there is no metric yet explicitly quantifying how well a drawing of a graph represents its cluster structure. We define a clustering quality metric measuring how well a node-link drawing of a graph represents the clusters contained in the graph. Experiments with deforming graph drawings verify that our metric effectively captures variations in the visual cluster quality of graph drawings. We then use our metric to examine how well different graph drawing algorithms visualize cluster structures in various graphs; the results con-firm that some algorithms which have been specifically designed to show cluster structures perform better than other algorithms.

[73]
Title: Pipe Roughness Identification of Water Distribution Networks: The Full Turbulent Case
Subjects: Systems and Control (eess.SY)

This paper proposes a technique to identify individual pipe roughness parameters in a water distribution network by means of the inversion of the steady-state hydraulic network equations. By enabling the reconstruction of these hydraulic friction parameters to be reliable, this technique improves the conventional model's accuracy and thereby promises to enhance model-based leakage detection and localization. As it is the case in so-called fireflow tests, this methodology is founded on the premise to measure the pressure distributed at a subset of nodes in the network's graph while assuming the nodal consumption to be known. Beside of the proposed problem formulation, which is restricted to only allow turbulent flow in each of the network's pipes initially, developed algorithms are presented and evaluated using simulation examples.

[74]
Title: Dialog State Tracking with Reinforced Data Augmentation
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate high-quality data to improve the neural state tracker. Specifically, we introduce a novel contextual bandit generator to learn fine-grained augmentation policies that can generate new effective instances by choosing suitable replacements for the specific context. Moreover, by alternately learning between the generator and the state tracker, we can keep refining the generative policies to generate more high-quality training data for neural state tracker. Experimental results on the WoZ and MultiWoZ (restaurant) datasets demonstrate that the proposed framework significantly improves the performance over the state-of-the-art models, especially with limited training data.

[75]
Title: InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated using data annotation from other domain (e.g. bbox, point) in a weakly supervised mechanism. In this paper, we present a simple, efficient and effective method to augment the training set using the existing instance mask annotations. Exploiting the pixel redundancy of the background, we are able to improve the performance of Mask R-CNN for 1.7 mAP on COCO dataset and 3.3 mAP on Pascal VOC dataset by simply introducing random jittering to objects. Furthermore, we propose a location probability map based approach to explore the feasible locations that objects can be placed based on local appearance similarity. With the guidance of such map, we boost the performance of R101-Mask R-CNN on instance segmentation from 35.7 mAP to 37.9 mAP without modifying the backbone or network structure. Our method is simple to implement and does not increase the computational complexity. It can be integrated into the training pipeline of any instance segmentation model without affecting the training and inference efficiency. Our code and models have been released at https://github.com/GothicAi/InstaBoost

[76]
Title: Event-Triggered Output Synchronization of Heterogeneous Nonlinear Multi-Agents
Comments: 12 pages, 5 figures, IEEE transaction
Journal-ref: CYB-E-2019-04-0672
Subjects: Systems and Control (eess.SY)

This paper addresses the output synchronization problem for heterogeneous nonlinear multi-agent systems with distributed event-based controllers. Employing the two-step synchronization process, we first outline the distributed event-triggered consensus controllers for linear reference models under a directed communication topology. It is further shown that the subsequent triggering instants are based on intermittent communication. Secondly, by using certain input-to-state stability (ISS) property, we design an event-triggered perturbed output regulation controller for each nonlinear multi-agent. The ISS technique used in this paper is based on the milder condition that each agent has a certain ISS property from input (actuator) disturbance to state rather than measurement (sensor) disturbance to state. With the two-step design, the objective of output synchronization is successfully achieved with Zeno behavior avoided.

[77]
Title: Exploring Offline Policy Evaluation for the Continuous-Armed Bandit Problem
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

The (contextual) multi-armed bandit problem (MAB) provides a formalization of sequential decision-making which has many applications. However, validly evaluating MAB policies is challenging; we either resort to simulations which inherently include debatable assumptions, or we resort to expensive field trials. Recently an offline evaluation method has been suggested that is based on empirical data, thus relaxing the assumptions, and can be used to evaluate multiple competing policies in parallel. This method is however not directly suited for the continuous armed (CAB) problem; an often encountered version of the MAB problem in which the action set is continuous instead of discrete. We propose and evaluate an extension of the existing method such that it can be used to evaluate CAB policies. We empirically demonstrate that our method provides a relatively consistent ranking of policies. Furthermore, we detail how our method can be used to select policies in a real-life CAB problem.

[78]
Title: Improving Captioning for Low-Resource Languages by Cycle Consistency
Subjects: Computation and Language (cs.CL); Multimedia (cs.MM)

Improving the captioning performance on low-resource languages by leveraging English caption datasets has received increasing research interest in recent years. Existing works mainly fall into two categories: translation-based and alignment-based approaches. In this paper, we propose to combine the merits of both approaches in one unified architecture. Specifically, we use a pre-trained English caption model to generate high-quality English captions, and then take both the image and generated English captions to generate low-resource language captions. We improve the captioning performance by adding the cycle consistency constraint on the cycle of image regions, English words, and low-resource language words. Moreover, our architecture has a flexible design which enables it to benefit from large monolingual English caption datasets. Experimental results demonstrate that our approach outperforms the state-of-the-art methods on common evaluation metrics. The attention visualization also shows that the proposed approach really improves the fine-grained alignment between words and image regions.

[79]
Title: Arabs and Atheism: Religious Discussions in the Arab Twittersphere
Comments: Accepted as a full paper at Socinfo 2019. Please cite the Socinfo version. In Proceedings of the 11th International Conference on Social Informatics (SocInfo 2019)
Subjects: Social and Information Networks (cs.SI)

Most previous research on online discussions of atheism has focused on atheism within a Christian context. In contrast, discussions about atheism in the Arab world and from Islamic background are relatively poorly studied. An added complication is that open atheism is against the law in some Arab countries, which may further restrict atheist activity on social media. In this work, we explore atheistic discussion in the Arab Twittersphere. We identify four relevant categories of Twitter users according to the content they post: atheistic, theistic, tanweeri (religious renewal), and other. We characterise the typical content posted by these four sets of users and their social networks, paying particular attention to the topics discussed and the interaction among them. Our findings have implication for the study of religious and spiritual discourse on social media and provide a better cross-cultural understanding of relevant aspects.

[80]
Title: A Multi-Turn Emotionally Engaging Dialog Model
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)

Open-domain dialog systems (also known as chatbots) have increasingly drawn attention in natural language processing. Some of the recent work aims at incorporating affect information into sequence-to-sequence neural dialog modeling, making the response emotionally richer, while others use hand-crafted rules to determine the desired emotion response. However, they do not explicitly learn the subtle emotional interactions captured in real human dialogs. In this paper, we propose a multi-turn dialog system capable of learning and generating emotional responses that so far only humans know how to do. Compared to two baseline models, offline experiments show that our method performs the best in perplexity scores. Further human evaluations confirm that our chatbot can keep track of the conversation context and generate emotionally more appropriate responses while performing equally well on grammar.

[81]
Title: Disentangling Latent Emotions of Word Embeddings on Complex Emotional Narratives
Comments: 9 pages, submitted and accepted by NLP conference 2019
Journal-ref: NLPCC2019
Subjects: Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG)

Word embedding models such as GloVe are widely used in natural language processing (NLP) research to convert words into vectors. Here, we provide a preliminary guide to probe latent emotions in text through GloVe word vectors. First, we trained a neural network model to predict continuous emotion valence ratings by taking linguistic inputs from Stanford Emotional Narratives Dataset (SEND). After interpreting the weights in the model, we found that only a few dimensions of the word vectors contributed to expressing emotions in text, and words were clustered on the basis of their emotional polarities. Furthermore, we performed a linear transformation that projected high dimensional embedded vectors into an emotion space. Based on NRC Emotion Lexicon (EmoLex), we visualized the entanglement of emotions in the lexicon by using both projected and raw GloVe word vectors. We showed that, in the proposed emotion space, we were able to better disentangle emotions than using raw GloVe vectors alone. In addition, we found that the sum vectors of different pairs of emotion words successfully captured expressed human feelings in the EmoLex. For example, the sum of two embedded word vectors expressing Joy and Trust which express Love shared high similarity (similarity score .62) with the embedded vector expressing Optimism. On the contrary, this sum vector was dissimilar (similarity score -.19) with the the embedded vector expressing Remorse. In this paper, we argue that through the proposed emotion space, arithmetic of emotions is preserved in the word vectors. The affective representation uncovered in emotion vector space could shed some light on how to help machines to disentangle emotion expressed in word embeddings.

[82]
Title: Replication of the Keyword Extraction part of the paper "'Without the Clutter of Unimportant Words': Descriptive Keyphrases for Text Visualization"
Subjects: Computation and Language (cs.CL); Digital Libraries (cs.DL); Information Retrieval (cs.IR)

"Keyword Extraction" refers to the task of automatically identifying the most relevant and informative phrases in natural language text. As we are deluged with large amounts of text data in many different forms and content - emails, blogs, tweets, Facebook posts, academic papers, news articles - the task of "making sense" of all this text by somehow summarizing them into a coherent structure assumes paramount importance. Keyword extraction - a well-established problem in Natural Language Processing - can help us here. In this report, we construct and test three different hypotheses (all related to the task of keyword extraction) that take us one step closer to understanding how to meaningfully identify and extract "descriptive" keyphrases. The work reported here was done as part of replicating the study by Chuang et al. [3].

[83]
Title: Rating for Parents: Predicting Children Suitability Rating for Movies Based on Language of the Movies
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)

The film culture has grown tremendously in recent years. The large number of streaming services put films as one of the most convenient forms of entertainment in today's world. Films can help us learn and inspire societal change. But they can also negatively affect viewers. In this paper, our goal is to predict the suitability of the movie content for children and young adults based on scripts. The criterion that we use to measure suitability is the MPAA rating that is specifically designed for this purpose. We propose an RNN based architecture with attention that jointly models the genre and the emotions in the script to predict the MPAA rating. We achieve 78% weighted F1-score for the classification model that outperforms the traditional machine learning method by 6%.

[84]
Title: An Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processing
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)

Multi-Task Learning (MTL) aims at boosting the overall performance of each individual task by leveraging useful information contained in multiple related tasks. It has shown great success in natural language processing (NLP). Currently, a number of MLT architectures and learning mechanisms have been proposed for various NLP tasks. However, there is no systematic exploration and comparison of different MLT architectures and learning mechanisms for their strong performance in-depth. In this paper, we conduct a thorough examination of typical MTL methods on a broad range of representative NLP tasks. Our primary goal is to understand the merits and demerits of existing MTL methods in NLP tasks, thus devising new hybrid architectures intended to combine their strengths.

[85]
Title: A Multi-level Neural Network for Implicit Causality Detection in Web Texts
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Mining causality from text is a complex and crucial natural language understanding task. Most of the early attempts at its solution can group into two categories: 1) utilizing co-occurrence frequency and world knowledge for causality detection; 2) extracting cause-effect pairs by using connectives and syntax patterns directly. However, because causality has various linguistic expressions, the noisy data and ignoring implicit expressions problems induced by these methods cannot be avoided. In this paper, we present a neural causality detection model, namely Multi-level Causality Detection Network (MCDN), to address this problem. Specifically, we adopt multi-head self-attention to acquire semantic feature at word level and integrate a novel Relation Network to infer causality at segment level. To the best of our knowledge, in touch with the causality tasks, this is the first time that the Relation Network is applied. The experimental results on the AltLex dataset, demonstrate that: a) MCDN is highly effective for the ambiguous and implicit causality inference; b) comparing with the regular text classification task, causality detection requires stronger inference capability; c) the proposed approach achieved state-of-the-art performance.

[86]
Title: Re-route Package Pickup and Delivery Planning with Random Demands
Comments: 6 pages, 4 figures, 2 tables
Journal-ref: 2019 IEEE 90th Vehicular Technology Conference: VTC2019-Fall
Subjects: Artificial Intelligence (cs.AI)

Recently, a higher competition in logistics business introduces new challenges to the vehicle routing problem (VRP). Re-route planning, also known as dynamic VRP, is one of the important challenges. The re-route planning has to be performed when new customers request for deliveries while the delivery vehicles, i.e., trucks, are serving other customers. While the re-route planning has been studied in the literature, most of the existing works do not consider different uncertainties. Therefore, in this paper, we propose two systems, i.e., (i) an offline package pickup and delivery planning with stochastic demands (PDPSD) and (ii) a re-route package pickup and delivery planning with stochastic demands (Re-route PDPSD). Accordingly, we formulate the PDPSD system as a two-stage stochastic optimization. We then extend the PDPSD system to the Re-route PDPSD system with a re-route algorithm. Furthermore, we evaluate performance of the proposed systems by using the dataset from Solomon Benchmark suite and a real data from a Singapore logistics 1company. The results show that the PDPSD system can achieve the lower cost than that of the baseline model. In addition, the Re-route PDPSD system can help the supplier efficiently and successfully to serve more customers while the trucks are already on the road.

[87]
Subjects: Cryptography and Security (cs.CR); Networking and Internet Architecture (cs.NI)

Supply chain is emerging as the next frontier of threats in the rapidly evolving IoT ecosystem. It is fundamentally more complex compared to traditional ICT systems. We analyze supply chain risks in IoT systems and their unique aspects, discuss research challenges in supply chain security, and identify future research directions.

[88]
Title: DNA based Network Model and Blockchain
Subjects: Other Computer Science (cs.OH); Cryptography and Security (cs.CR)

Biological cells can transmit, process and receive chemically encoded data in the same way as network devices transmit, process, and receive digitally encoded data. Communication protocols have led to the rapid development of computer networks. Therefore, we need to develop communication protocols for biological cell networks, which will lead to significant development, especially in medical applications where surgery or delivery of drugs can be performed using nanoscale devices. Blockchain is a peer-to-peer network that contains a series of clusters to make a valid and secure transaction. Blockhain technology is used in many areas such as e-commerce, public services, security, finance, Internet stuff, etc. Although blockchain has a major impact on Internet technology, it suffers from time problems and scalability. DNA computing is the execution of computations using natural molecules, especially DNA. DNA gaps above silicon because of massive parallelism, size and storage density. In this paper, biological cells and DNA are used to create the necessary protocols for the networks to be used in the performance of the cell-based communication system. The proposed hybrid solution involves DNA as well as calculated on an enzymatic basis, where each contributes to the function of a given protocol. Also a correspondence between blockchain and DNA is proposed that can be utilized to create DNA based blockchain.

[89]
Title: Polly Want a Cracker: Analyzing Performance of Parroting on Paraphrase Generation Datasets
Subjects: Computation and Language (cs.CL)

Paraphrase generation is an interesting and challenging NLP task which has numerous practical applications. In this paper, we analyze datasets commonly used for paraphrase generation research, and show that simply parroting input sentences surpasses state-of-the-art models in the literature when evaluated on standard metrics. Our findings illustrate that a model could be seemingly adept at generating paraphrases, despite only making trivial changes to the input sentence or even none at all.

[90]
Title: Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Machine Learning (stat.ML)

Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures. Word-level analysis cannot leverage the semantic information present in such subword structures. With regard to word embedding techniques, this leads to not only poor embeddings for infrequent words in long-tailed text corpora but also weak capabilities for handling out-of-vocabulary words. In this paper we propose MorphMine for unsupervised morpheme segmentation. MorphMine applies a parsimony criterion to hierarchically segment words into the fewest number of morphemes at each level of the hierarchy. This leads to longer shared morphemes at each level of segmentation. Experiments show that MorphMine segments words in a variety of languages into human-verified morphemes. Additionally, we experimentally demonstrate that utilizing MorphMine morphemes to enrich word embeddings consistently improves embedding quality on a variety of of embedding evaluations and a downstream language modeling task.

[91]
Title: Memory Forensic Analysis of MQTT Devices
Comments: 4 pages, 7 figures, 2 tables
Subjects: Cryptography and Security (cs.CR)

Internet of Things is revolutionizing the current era with its vast usage in number of fields such as medicine, automation, home security, smart cities, etc. As these IoT devices' uses are increasing, the threat to its security and to its application protocols are also increasing. Traffic passing over these protocol if intercepted, could reveal sensitive information and result in taking control of the entire IoT network. Scope of this paper is limited to MQTT protocol. MQTT (MQ Telemetry Transport) is a light weight protocol used for communication between IoT devices. There are multiple brokers as well as clients available for publishing and subscribing to services. For security purpose, it is essential to secure the traffic, broker and end client application. This paper demonstrates extraction of sensitive data from the devices which are running broker and client application.

[92]
Title: PubLayNet: largest dataset ever for document layout analysis
Subjects: Computation and Language (cs.CL)

Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this paper, we develop the PubLayNet dataset for document layout analysis by automatically matching the XML representations and the content of over 1 million PDF articles that are publicly available on PubMed Central. The size of the dataset is comparable to established computer vision datasets, containing over 360 thousand document images, where typical document layout elements are annotated. The experiments demonstrate that deep neural networks trained on PubLayNet accurately recognize the layout of scientific articles. The pre-trained models are also a more effective base mode for transfer learning on a different document domain. We release the dataset (https://github.com/ibm-aur-nlp/PubLayNet) to support development and evaluation of more advanced models for document layout analysis.

[93]
Title: Real-time Person Re-identification at the Edge: A Mixed Precision Approach
Comments: This is a pre-print of an article published in International Conference on Image Analysis and Recognition (ICIAR 2019), Lecture Notes in Computer Science. The final authenticated version is available online at this https URL
Journal-ref: International Conference on Image Analysis and Recognition (ICIAR 2019), Lecture Notes in Computer Science
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)

A critical part of multi-person multi-camera tracking is person re-identification (re-ID) algorithm, which recognizes and retains identities of all detected unknown people throughout the video stream. Many re-ID algorithms today exemplify state of the art results, but not much work has been done to explore the deployment of such algorithms for computation and power constrained real-time scenarios. In this paper, we study the effect of using a light-weight model, MobileNet-v2 for re-ID and investigate the impact of single (FP32) precision versus half (FP16) precision for training on the server and inference on the edge nodes. We further compare the results with the baseline model which uses ResNet-50 on state of the art benchmarks including CUHK03, Market-1501, and Duke-MTMC. The MobileNet-V2 mixed precision training method can improve both inference throughput on the edge node, and training time on server $3.25\times$ reaching to 27.77fps and $1.75\times$, respectively and decreases power consumption on the edge node by $1.45\times$, while it deteriorates accuracy only 5.6\% in respect to ResNet-50 single precision on the average for three different datasets. The code and pre-trained networks are publicly available at https://github.com/TeCSAR-UNCC/person-reid.

[94]
Title: Similarity Learning for Authorship Verification in Social Media
Comments: 5 pages, 3 figures, 1 table, presented on ICASSP 2019 in Brighton, UK
Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Machine Learning (stat.ML)

Authorship verification tries to answer the question if two documents with unknown authors were written by the same author or not. A range of successful technical approaches has been proposed for this task, many of which are based on traditional linguistic features such as n-grams. These algorithms achieve good results for certain types of written documents like books and novels. Forensic authorship verification for social media, however, is a much more challenging task since messages tend to be relatively short, with a large variety of different genres and topics. At this point, traditional methods based on features like n-grams have had limited success. In this work, we propose a new neural network topology for similarity learning that significantly improves the performance on the author verification task with such challenging data sets.

[95]
Title: A novel text representation which enables image classifiers to perform text classification, applied to name disambiguation
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Patent data are often used to study the process of innovation and research, but patent databases lack unique identifiers for individual inventors, making it difficult to study innovation processes at the individual level. Here we introduce an algorithm that performs highly accurate disambiguation of inventors (named entities) in US patent data (F1: 99.09%, precision: 99.41%, recall: 98.76%). The algorithm involves a novel method for converting text-based record data into abstract image representations, in which text from a given pairwise comparison between two inventor name records is converted into a 2D RGB (stacked) image representation. We train an image classification neural network to discriminate between such pairwise comparison images, and then use the trained network to label each pair of records as either matched (same inventor) or non-matched (different inventors). The resulting disambiguation algorithm produces highly accurate results, out-performing other inventor name disambiguation studies on US patent data. Our new text-to-image representation method could potentially be used more broadly for other NLP comparison problems, as it allows image-based processing techniques (e.g. image classification networks) to be applied to text-based comparison problems (such as disambiguation of academic publications, or data linkage problems).

[96]
Title: CUDA optimized Neural Network predicts blood glucose control from quantified joint mobility and anthropometrics
Comments: 5 pages, 6 figures, conference paper: International Conference on Information System and Data Mining, published at this https URL
Subjects: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM); Machine Learning (stat.ML)

Neural network training entails heavy computation with obvious bottlenecks. The Compute Unified Device Architecture (CUDA) programming model allows us to accelerate computation by passing the processing workload from the CPU to the graphics processing unit (GPU). In this paper, we leveraged the power of Nvidia GPUs to parallelize all of the computation involved in training, to accelerate a backpropagation feed-forward neural network with one hidden layer using CUDA and C++. This optimized neural network was tasked with predicting the level of glycated hemoglobin (HbA1c) from non-invasive markers. The rate of increase in the prevalence of Diabetes Mellitus has resulted in an urgent need for early detection and accurate diagnosis. However, due to the invasiveness and limitations of conventional tests, alternate means are being considered. Limited Joint Mobility (LJM) has been reported as an indicator for poor glycemic control. LJM of the fingers is quantified and its link to HbA1c is investigated along with other potential non-invasive markers of HbA1c. We collected readings of 33 potential markers from 120 participants at a clinic in south Trinidad. Our neural network achieved 95.65% accuracy on the training and 86.67% accuracy on the testing set for male participants and 97.73% and 66.67% accuracy on the training and testing sets for female participants. Using 960 CUDA cores from a Nvidia GeForce GTX 660, our parallelized neural network was trained 50 times faster on both subsets, than its corresponding CPU implementation on an Intel Core (TM) i7-3630QM 2.40 GHz CPU.

[97]
Title: GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level
Comments: 6 pages, to appear at the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019)
Subjects: Computation and Language (cs.CL)

Scenario-based question answering (SQA) has attracted increasing research attention. It typically requires retrieving and integrating knowledge from multiple sources, and applying general knowledge to a specific case described by a scenario. SQA widely exists in the medical, geography, and legal domains---both in practice and in the exams. In this paper, we introduce the GeoSQA dataset. It consists of 1,981 scenarios and 4,110 multiple-choice questions in the geography domain at high school level, where diagrams (e.g., maps, charts) have been manually annotated with natural language descriptions to benefit NLP research. Benchmark results on a variety of state-of-the-art methods for question answering, textual entailment, and reading comprehension demonstrate the unique challenges presented by SQA for future research.

[98]
Title: Multi-hypothesis classifier
Subjects: Machine Learning (cs.LG)

Accuracy is the most important parameter among few others which defines the effectiveness of a machine learning algorithm. Higher accuracy is always desirable. Now, there is a vast number of well established learning algorithms already present in the scientific domain. Each one of them has its own merits and demerits. Merits and demerits are evaluated in terms of accuracy, speed of convergence, complexity of the algorithm, generalization property, and robustness among many others. Also the learning algorithms are data-distribution dependent. Each learning algorithm is suitable for a particular distribution of data. Unfortunately, no dominant classifier exists for all the data distribution, and the data distribution task at hand is usually unknown. Not one classifier can be discriminative well enough if the number of classes are huge. So the underlying problem is that a single classifier is not enough to classify the whole sample space correctly. This thesis is about exploring the different techniques of combining the classifiers so as to obtain the optimal accuracy. Three classifiers are implemented namely plain old nearest neighbor on raw pixels, a structural feature extracted neighbor and Gabor feature extracted nearest neighbor. Five different combination strategies are devised and tested on Tibetan character images and analyzed

[99]
Title: Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery
Comments: Accepted by ICDM 2019 as a regular paper
Subjects: Computer Vision and Pattern Recognition (cs.CV)

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2,1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery.

[100]
Title: Federated Learning: Challenges, Methods, and Future Directions
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (stat.ML)

Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.

[101]
Title: Analog circuits for mixed-signal neuromorphic computing architectures in 28 nm FD-SOI technology
Comments: 2017 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference (S3S)
Subjects: Emerging Technologies (cs.ET)

Developing mixed-signal analog-digital neuromorphic circuits in advanced scaled processes poses significant design challenges. We present compact and energy efficient sub-threshold analog synapse and neuron circuits, optimized for a 28 nm FD-SOI process, to implement massively parallel large-scale neuromorphic computing systems. We describe the techniques used for maximizing density with mixed-mode analog/digital synaptic weight configurations, and the methods adopted for minimizing the effect of channel leakage current, in order to implement efficient analog computation based on pA-nA small currents. We present circuit simulation results, based on a new chip that has been recently taped out, to demonstrate how the circuits can be useful for both low-frequency operation in systems that need to interact with the environment in real-time, and for high-frequency operation for fast data processing in different types of spiking neural network architectures.

[102]
Title: Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification
Comments: Accepted by ICDM 2019 as a regular paper
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

In this paper, we extend the popular dictionary pair learning (DPL) into the scenario of twin-projective latent flexible DPL under a structured twin-incoherence. Technically, a novel framework called Twin-Projective Latent Flexible DPL (TP-DPL) is proposed, which minimizes the twin-incoherence constrained flexibly-relaxed reconstruction error to avoid the possible over-fitting issue and produce accurate reconstruction. In this setting, our TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner. As a result, TP-DPL unifies the salient feature extraction, representation and classification. The twin-incoherence constraint on codes and features can explicitly ensure high intra-class compactness and inter-class separation over them. TP-DPL also integrates the adaptive weighting to preserve the local neighborhood of the coefficients and salient features within each class explicitly. For efficiency, TP-DPL uses Frobenius-norm and abandons the costly l0/l1-norm for group sparse representation. Another byproduct is that TP-DPL can directly apply the class-specific twin-projective reconstruction residual to compute the label of data. Extensive results on public databases show that TP-DPL can deliver the state-of-the-art performance.

[103]
Title: Universal Reconfiguration of Facet-Connected Modular Robots by Pivots: The $O(1)$ Musketeers
Subjects: Computational Geometry (cs.CG); Robotics (cs.RO)

We present the first universal reconfiguration algorithm for transforming a modular robot between any two facet-connected square-grid configurations using pivot moves. More precisely, we show that five extra "helper" modules ("musketeers") suffice to reconfigure the remaining $n$ modules between any two given configurations. Our algorithm uses $O(n^2)$ pivot moves, which is worst-case optimal. Previous reconfiguration algorithms either require less restrictive "sliding" moves, do not preserve facet-connectivity, or for the setting we consider, could only handle a small subset of configurations defined by a local forbidden pattern. Configurations with the forbidden pattern do have disconnected reconfiguration graphs (discrete configuration spaces), and indeed we show that they can have an exponential number of connected components. But forbidding the local pattern throughout the configuration is far from necessary, as we show that just a constant number of added modules (placed to be freely reconfigurable) suffice for universal reconfigurability. We also classify three different models of natural pivot moves that preserve facet-connectivity, and show separations between these models.

[104]
Title: Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR); Machine Learning (stat.ML)

In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these models. The results show that previous Lipschitz regularization techniques are effective in not only reducing the generalization gap but also alleviating the information leakage of the training dataset.

[105]
Title: Scala Implicits are Everywhere: A large-scale study of the use of Implicits in the wild
Subjects: Programming Languages (cs.PL); Software Engineering (cs.SE)

The Scala programming language offers two distinctive language features implicit parameters and implicit conversions, often referred together as implicits. Announced without fanfare in 2004, implicits have quickly grown to become a widely and pervasively used feature of the language. They provide a way to reduce the boilerplate code in Scala programs. They are also used to implement certain language features without having to modify the compiler. We report on a large-scale study of the use of implicits in the wild. For this, we analyzed 7,280 Scala projects hosted on GitHub, spanning over 8.1M call sites involving implicits and 370.7K implicit declarations across 18.7M lines of Scala code.

[106]
Title: Representation Disentanglement for Multi-task Learning with application to Fetal Ultrasound
Subjects: Machine Learning (cs.LG); Image and Video Processing (eess.IV); Machine Learning (stat.ML)

[107]
Title: Detecting Fraudulent Accounts on Blockchain: A Supervised Approach
Subjects: Cryptography and Security (cs.CR)

Applications of blockchain technologies got a lot of attention in recent years. They exceed beyond exchanging value and being a substitute for fiat money and traditional banking system. Nevertheless, being able to exchange value on a blockchain is at the core of the entire system and has to be reliable. Blockchains have built-in mechanisms that guarantee whole system's consistency and reliability. However, malicious actors can still try to steal money by applying well known techniques like malware software or fake emails. In this paper we apply supervised learning techniques to detect fraudulent accounts on Ethereum blockchain. We compare capabilities of Random Forests, Support Vector Machines and XGBoost classifiers to identify such accounts basing on a dataset of more than 300 thousands accounts. Results show that we are able to achieve recall and precision values allowing for the designed system to be applicable as an anti-fraud rule for digital wallets or currency exchanges. We also present sensitivity analysis to show how presented models depend on particular feature and how lack of some of them will affect the overall system performance.

[108]
Title: Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition
Subjects: Computation and Language (cs.CL)

In this paper, we present a method for correcting automatic speech recognition (ASR) errors using a finite state transducer (FST) intent recognition framework. Intent recognition is a powerful technique for dialog flow management in turn-oriented, human-machine dialogs. This technique can also be very useful in the context of human-human dialogs, though it serves a different purpose of key insight extraction from conversations. We argue that currently available intent recognition techniques are not applicable to human-human dialogs due to the complex structure of turn-taking and various disfluencies encountered in spontaneous conversations, exacerbated by speech recognition errors and scarcity of domain-specific labeled data. Without efficient key insight extraction techniques, raw human-human dialog transcripts remain significantly unexploited.
Our contribution consists of a novel FST for intent indexing and an algorithm for fuzzy intent search over the lattice - a compact graph encoding of ASR's hypotheses. We also develop a pruning strategy to constrain the fuzziness of the FST index search. Extracted intents represent linguistic domain knowledge and help us improve (rescore) the original transcript. We compare our method with a baseline, which uses only the most likely transcript hypothesis (best path), and find an increase in the total number of recognized intents by 25%.

[109]
Title: Visualization in the preprocessing phase: an interview study with enterprise professionals
Comments: 11 pages with references; 5 figures
Subjects: Human-Computer Interaction (cs.HC)

The current information age has increasingly required organizations to become data-driven. However, analyzing and managing raw data is still a challenging part of the data mining process. Even though we can find interview studies proposing design implications or recommendations for future visualization solutions in the data mining scope, they cover the entire workflow and do not fully focus on the challenges during the preprocessing phase and on how visualization can support it. Moreover, they do not organize a final list of insights consolidating the findings of other related studies. Hence, to better understand the current practice of enterprise professionals in data mining workflows, in particular during the preprocessing phase, and how visualization supports this process, we conducted semi-structured interviews with thirteen data analysts. The discussion about the challenges and opportunities based on the responses of the interviewees resulted in a list of ten insights. This list was compared with the closest related works, improving the reliability of our findings and providing background, as a consolidated set of requirements, for future visualization research papers applied to visual data exploration in data mining. Furthermore, we provide greater details on the profile of the data analysts, the main challenges they face, and the opportunities that arise while they are engaged in data mining projects in diverse organizational areas.

[110]
Title: Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
Subjects: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)

Continuing advances in neural interfaces have enabled simultaneous monitoring of spiking activity from hundreds to thousands of neurons. To interpret these large-scale data, several methods have been proposed to infer latent dynamic structure from high-dimensional datasets. One recent line of work uses recurrent neural networks in a sequential autoencoder (SAE) framework to uncover dynamics. SAEs are an appealing option for modeling nonlinear dynamical systems, and enable a precise link between neural activity and behavior on a single-trial basis. However, the very large parameter count and complexity of SAEs relative to other models has caused concern that SAEs may only perform well on very large training sets. We hypothesized that with a method to systematically optimize hyperparameters (HPs), SAEs might perform well even in cases of limited training data. Such a breakthrough would greatly extend their applicability. However, we find that SAEs applied to spiking neural data are prone to a particular form of overfitting that cannot be detected using standard validation metrics, which prevents standard HP searches. We develop and test two potential solutions: an alternate validation method ("sample validation") and a novel regularization method ("coordinated dropout"). These innovations prevent overfitting quite effectively, and allow us to test whether SAEs can achieve good performance on limited data through large-scale HP optimization. When applied to data from motor cortex recorded while monkeys made reaches in various directions, large-scale HP optimization allowed SAEs to better maintain performance for small dataset sizes. Our results should greatly extend the applicability of SAEs in extracting latent dynamics from sparse, multidimensional data, such as neural population spiking activity.

[111]
Title: Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets
Subjects: Computation and Language (cs.CL)

Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years. A common crowdsourcing practice is to recruit a small number of high-quality workers, and have them massively generate examples. Having only a few workers generate the majority of examples raises concerns about data diversity, especially when workers freely generate sentences. In this paper, we perform a series of experiments showing these concerns are evident in three recent NLP datasets. We show that model performance improves when training with annotator identifiers as features, and that models are able to recognize the most productive annotators. Moreover, we show that often models do not generalize well to examples from annotators that did not contribute to the training set. Our findings suggest that annotator bias should be monitored during dataset creation, and that test set annotators should be disjoint from training set annotators.

[112]
Title: Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples
Comments: Published at the International Conference on Artificial Neural Networks (ICANN) 2019
Subjects: Computation and Language (cs.CL); Cryptography and Security (cs.CR); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)

[113]
Title: Energy Management of Airport Service Electric Vehicles to Match Renewable Generation through Rollout Approach
Authors: Renjie Wei, Kang Ma
Subjects: Systems and Control (eess.SY)

Traditional diesel-based airport service vehicles are characterized by a heavy-duty, high-usage-frequency nature and a high carbon intensity per vehicle per hour. Transforming these vehicles into electric vehicles would reduce CO2 emissions and potentially save energy costs in the context of rising fuel prices, if a proper energy management of airport service electric vehicles (ASEVs) is performed. To perform such an energy management, this paper proposes a new customized rollout approach, as a near-optimal control method for a new ASEV dynamics model, which models the ASEV states, their transitions over time, and how control decisions affect them. The rollout approach yields a near-optimal control strategy for the ASEVs to transport luggage and to charge batteries, with the objective to minimize the operation cost, which incentivizes the charging of the ASEVs to match renewable generation. Case studies demonstrate that the rollout approach effectively overcomes the "curse of dimensionality". On both typical summer and winter days, the rollout algorithm results in a total cost approximately 10% less than that of the underlying "greedy charging" heuristic, which charges a battery whenever its state of charge is not the maximum. The rollout algorithm is proven to be adaptive towards flight schedule changes at short notice.

[114]
Title: Energy Efficient Routing and Network Coding in Core Networks
Subjects: Networking and Internet Architecture (cs.NI)

We propose network coding as an energy efficient data transmission technique in core networks with non-bypass and bypass routing approaches. The improvement in energy efficiency is achieved through reduction in the traffic flows passing through intermediate nodes. A mixed integer linear program (MILP) is developed to optimize the use of network resources, and the results show that our proposed network coding approach introduces up to 33% power savings for the non-bypass case compared with the conventional architectures. For the bypass case, 28% power savings are obtained considering futuristic network components power consumption. A heuristic based on the minimum hop count routing shows power savings comparable to the MILP results. Furthermore, we study how the change in network topology affects the savings produced by network coding. The results show that the savings are proportional to the average hop count of the network topology. We also derive power consumption analytic bounds and closed form expressions for networks that implement network coding and thus also verify the results obtained by the MILP model.

[115]
Title: Effects of Blur and Deblurring to Visual Object Tracking
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Intuitively, motion blur may hurt the performance of visual object tracking. However, we lack quantitative evaluation of tracker robustness to different levels of motion blur. Meanwhile, while image deblurring methods can produce visually clearer videos for pleasing human eyes, it is unknown whether visual object tracking can benefit from image deblurring or not. In this paper, we address these two problems by constructing a Blurred Video Tracking benchmark, which contains a variety of videos with different levels of motion blurs, as well as ground truth tracking results for evaluating trackers. We extensively evaluate 23 trackers on this benchmark and observe several new interesting results. Specifically, we find that light blur may improve the performance of many trackers, but heavy blur always hurts the tracking performance. We also find that image deblurring may help to improve tracking performance on heavily blurred videos but hurt the performance on lightly blurred videos. According to these observations, we propose a new GAN based scheme to improve the tracker robustness to motion blurs. In this scheme, a finetuned discriminator is used as an adaptive assessor to selectively deblur frames during the tracking process. We use this scheme to successfully improve the accuracy and robustness of 6 trackers.

[116]
Title: DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking
Journal-ref: 14th International Symposium on Visual Computing (ISVC2019)
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Visual object tracking is a fundamental task in the field of computer vision. Recently, Siamese trackers have achieved state-of-the-art performance on recent benchmarks. However, Siamese trackers do not fully utilize semantic and objectness information from pre-trained networks that have been trained on the image classification task. Furthermore, the pre-trained Siamese architecture is sparsely activated by the category label which leads to unnecessary calculations and overfitting. In this paper, we propose to learn a Domain-Aware, that is fully utilizing semantic and objectness information while producing a class-agnostic using a ridge regression network. Moreover, to reduce the sparsity problem, we solve the ridge regression problem with a differentiable weighted-dynamic loss function. Our tracker, dubbed DomainSiam, improves the feature learning in the training phase and generalization capability to other domains. Extensive experiments are performed on five tracking benchmarks including OTB2013 and OTB2015 for a validation set; as well as the VOT2017, VOT2018, LaSOT, TrackingNet, and GOT10k for a testing set. DomainSiam achieves state-of-the-art performance on these benchmarks while running at 53 FPS.

[117]
Title: PCRNet: Point Cloud Registration Network using PointNet Encoding
Subjects: Computer Vision and Pattern Recognition (cs.CV)

PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion. However, recent works in literature have shown the sensitivity of the PointNet representation to pose misalignment. This paper presents a novel framework that uses the PointNet representation to align point clouds and perform registration for applications such as tracking, 3D reconstruction and pose estimation. We develop a framework that compares PointNet features of template and source point clouds to find the transformation that aligns them accurately. Depending on the prior information about the shape of the object formed by the point clouds, our framework can produce approaches that are shape specific or general to unseen shapes. The shape specific approach uses a Siamese architecture with fully connected (FC) layers and is robust to noise and initial misalignment in data. We perform extensive simulation and real-world experiments to validate the efficacy of our approach and compare the performance with state-of-art approaches.

[118]
Title: It Takes Nine to Smell a Rat: Neural Multi-Task Learning for Check-Worthiness Prediction
Journal-ref: RANLP-2019
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

We propose a multi-task deep-learning approach for estimating the check-worthiness of claims in political debates. Given a political debate, such as the 2016 US Presidential and Vice-Presidential ones, the task is to predict which statements in the debate should be prioritized for fact-checking. While different fact-checking organizations would naturally make different choices when analyzing the same debate, we show that it pays to learn from multiple sources simultaneously (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post) in a multi-task learning setup, even when a particular source is chosen as a target to imitate. Our evaluation shows state-of-the-art results on a standard dataset for the task of check-worthiness prediction.

[119]
Title: Privacy-Preserving Support Vector Machine Computing Using Random Unitary Transformation
Comments: to be published in IEICE Trans. Fundamentals. arXiv admin note: substantial text overlap with arXiv:1809.07055
Subjects: Cryptography and Security (cs.CR)

A privacy-preserving support vector machine (SVM) computing scheme is proposed in this paper. Cloud computing has been spreading in many fields. However, the cloud computing has some serious issues for end users, such as the unauthorized use of cloud services, data leaks, and privacy being compromised. Accordingly, we consider privacy-preserving SVM computing. We focus on protecting visual \red{information} of images by using a random unitary transformation. Some properties of the protected images are discussed. The proposed scheme enables us not only to protect images, but also to have the same performance as that of unprotected images even when using typical kernel functions such as the linear kernel, radial basis function(RBF) kernel and polynomial kernel. Moreover, it can be directly carried out by using well-known SVM algorithms, without preparing any algorithms specialized for secure SVM computing. In an experiment, the proposed scheme is applied to a face-based authentication algorithm with SVM classifiers to confirm the effectiveness.

[120]
Title: Discrete Total Variation of the Normal Vector Field as Shape Prior with Applications in Geometric Inverse Problems
Subjects: Numerical Analysis (math.NA)

An analogue of the total variation prior for the normal vector field along the boundary of piecewise flat shapes in 3D is introduced. A major class of examples are triangulated surfaces as they occur for instance in finite element computations. The analysis of the functional is based on a differential geometric setting in which the unit normal vector is viewed as an element of the two-dimensional sphere manifold. It is found to agree with the discrete total mean curvature known in discrete differential geometry. A split Bregman iteration is proposed for the solution of discretized shape optimization problems, in which the total variation of the normal appears as a regularizer. Unlike most other priors, such as surface area, the new functional allows for piecewise flat shapes. As two applications, a mesh denoising and a geometric inverse problem of inclusion detection type involving a partial differential equation are considered. Numerical experiments confirm that polyhedral shapes can be identified quite accurately.

[121]
Title: Nuova frontiera della classificazione testuale: Big data e calcolo distribuito
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC)

This document was created in order to study the algorithms for the categorization of phrases and rank them using the facilities provided by the framework Apache Spark. Starting from the study illustrated in the publication "Classifying textual data: shallow, deep and ensemble methods" by Laura Anderlucci, Lucia Guastadisegni, Cinzia Viroli, we wanted to carry out a study on the possible realization of a solution that uses the distributed environment and allows the classification of phrases. Italiano. Il presente documento persegue l'obiettivo di studiare gli algoritmi per la categorizzazione di frasi e classificarle con l'ausilio delle strutture messe a disposizione dal framework Apache Spark. Partendo dallo studio illustrato nella pubblicazione "Classifying textual data: shallow, deep and ensemble methods" di Laura Anderlucci, Lucia Guastadisegni e Cinzia Viroli si \`e voluto realizzare uno studio sulla possibile implementazione di una soluzione in grado di classificare frasi sfruttando i l'ambiente distribuito.

[122]
Title: Mining Association Rules in Various Computing Environments: A Survey
Journal-ref: International Journal of Applied Engineering Research 2016; 11(8): 5629-5640
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Databases (cs.DB); Machine Learning (cs.LG)

Association Rule Mining (ARM) is one of the well know and most researched technique of data mining. There are so many ARM algorithms have been designed that their counting is a large number. In this paper we have surveyed the various ARM algorithms in four computing environments. The considered computing environments are sequential computing, parallel and distributed computing, grid computing and cloud computing. With the emergence of new computing paradigm, ARM algorithms have been designed by many researchers to improve the efficiency by utilizing the new paradigm. This paper represents the journey of ARM algorithms started from sequential algorithms, and through parallel and distributed, and grid based algorithms to the current state-of-the-art, along with the motives for adopting new machinery.

[123]
Title: Deep High-Resolution Representation Learning for Visual Recognition
Subjects: Computer Vision and Pattern Recognition (cs.CV)

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams \emph{in parallel}; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at~{\url{https://github.com/HRNet}}.

[124]
Title: Data Management for Causal Algorithmic Fairness
Subjects: Databases (cs.DB); Machine Learning (cs.LG)

Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflects discrimination, suggesting a data management problem. In this paper, we first make a distinction between associational and causal definitions of fairness in the literature and argue that the concept of fairness requires causal reasoning. We then review existing works and identify future opportunities for applying data management techniques to causal algorithmic fairness.

[125]
Title: Design Space of Behaviour Planning for Autonomous Driving
Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE)

We explore the complex design space of behaviour planning for autonomous driving. Design choices that successfully address one aspect of behaviour planning can critically constrain others. To aid the design process, in this work we decompose the design space with respect to important choices arising from the current state of the art approaches, and describe the resulting trade-offs. In doing this, we also identify interesting directions of future work.

[126]
Title: Design space exploration of Ferroelectric FET based Processing-in-Memory DNN Accelerator
Subjects: Emerging Technologies (cs.ET); Neural and Evolutionary Computing (cs.NE); Signal Processing (eess.SP)

In this letter, we quantify the impact of device limitations on the classification accuracy of an artificial neural network, where the synaptic weights are implemented in a Ferroelectric FET (FeFET) based in-memory processing architecture. We explore a design-space consisting of the resolution of the analog-to-digital converter, number of bits per FeFET cell, and the neural network depth. We show how the system architecture, training models and overparametrization can address some of the device limitations.

[127]
Title: Auction Algorithms for Market Equilibrium with Weak Gross Substitute Demands
Subjects: Computer Science and Game Theory (cs.GT)

We consider the exchange market models with divisible goods where the demands of the agents satisfy the weak gross substitutes (WGS) property. This is a well-studied property, in particular, it gives a sufficient condition for the convergence of the classical tatonnement dynamics. In this paper, we present a simple auction algorithm that obtains an approximate market equilibrium for WGS demands. Such auction algorithms have been previously known for restricted classes of WGS demands only. As an application of our result, we obtain an efficient algorithm to find an approximate spending-restricted market equilibrium for WGS demands, a model that has been recently introduced as a continuous relaxation of the Nash Social Welfare problem.

[128]
Title: Spectral estimates for saddle point matrices arising in weak constraint four-dimensional variational data assimilation
Subjects: Numerical Analysis (math.NA); Dynamical Systems (math.DS)

We consider the large-sparse symmetric linear systems of equations that arise in the solution of weak constraint four-dimensional variational data assimilation. These systems can be written as saddle point systems with a 3x3 block structure but block eliminations can be performed to reduce them to saddle point systems with a 2x2 block structure, or further to symmetric positive definite systems. In this paper, we analyse how sensitive the spectra of these matrices are to the number of observations of the underlying dynamical system. We also obtain bounds on the eigenvalues of the matrices. Numerical experiments are used to confirm the theoretical analysis and bounds.

[129]
Title: Non-negative Sparse and Collaborative Representation for Pattern Classification
Comments: 26 pages, 11 tables, 3 figures. arXiv admin note: text overlap with arXiv:1806.04329
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Sparse representation (SR) and collaborative representation (CR) have been successfully applied in many pattern classification tasks such as face recognition. In this paper, we propose a novel Non-negative Sparse and Collaborative Representation (NSCR) for pattern classification. The NSCR representation of each test sample is obtained by seeking a non-negative sparse and collaborative representation vector that represents the test sample as a linear combination of training samples. We observe that the non-negativity can make the SR and CR more discriminative and effective for pattern classification. Based on the proposed NSCR, we propose a NSCR based classifier for pattern classification. Extensive experiments on benchmark datasets demonstrate that the proposed NSCR based classifier outperforms the previous SR or CR based approach, as well as state-of-the-art deep approaches, on diverse challenging pattern classification tasks.

[130]
Title: Estimation of perceptual scales using ordinal embedding
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)

In this paper, we address the problem of measuring and analysing sensation, the subjective magnitude of one's experience. We do this in the context of the method of triads: the sensation of the stimulus is evaluated via relative judgments of the form: "Is stimulus S_i more similar to stimulus S_j or to stimulus S_k?". We propose to use ordinal embedding methods from machine learning to estimate the scaling function from the relative judgments. We review two relevant and well-known methods in psychophysics which are partially applicable in our setting: non-metric multi-dimensional scaling (NMDS) and the method of maximum likelihood difference scaling (MLDS). We perform an extensive set of simulations, considering various scaling functions, to demonstrate the performance of the ordinal embedding methods. We show that in contrast to existing approaches our ordinal embedding approach allows, first, to obtain reasonable scaling function from comparatively few relative judgments, second, the estimation of non-monotonous scaling functions, and, third, multi-dimensional perceptual scales. In addition to the simulations, we analyse data from two real psychophysics experiments using ordinal embedding methods. Our results show that in the one-dimensional, monotonically increasing perceptual scale our ordinal embedding approach works as well as MLDS, while in higher dimensions, only our ordinal embedding methods can produce a desirable scaling function. To make our methods widely accessible, we provide an R-implementation and general rules of thumb on how to use ordinal embedding in the context of psychophysics.

[131]
Title: Constrained Thompson Sampling for Real-Time Electricity Pricing with Grid Reliability Constraints
Comments: 10 pages, 6 figures, Preprint
Subjects: Systems and Control (eess.SY)

We consider the problem of an aggregator attempting to learn customers' load flexibility models while implementing a load shaping program by means of broadcasting daily dispatch signals. We adopt a multi-armed bandit formulation to account for the stochastic and unknown nature of customers' responses to dispatch signals. We propose a constrained Thompson sampling heuristic, Con-TS-RTP, that accounts for various possible aggregator objectives (e.g., to reduce demand at peak hours, integrate more intermittent renewable generation, track a desired daily load profile, etc) and takes into account the operational constraints of a distribution system to avoid potential grid failures as a result of uncertainty in the customers' response. We provide a discussion on the regret bounds for our algorithm as well as a discussion on the operational reliability of the distribution system's constraints being upheld throughout the learning process.

[132]
Title: Case Study: Disclosure of Indirect Device Fingerprinting in Privacy Policies
Subjects: Computers and Society (cs.CY)

Recent developments in online tracking make it harder for individuals to detect and block trackers. Some sites have deployed indirect tracking methods, which attempt to uniquely identify a device by asking the browser to perform a seemingly-unrelated task. One type of indirect tracking, Canvas fingerprinting, causes the browser to render a graphic recording rendering statistics as a unique identifier. In this work, we observe how indirect device fingerprinting methods are disclosed in privacy policies, and consider whether the disclosures are sufficient to enable website visitors to block the tracking methods. We compare these disclosures to the disclosure of direct fingerprinting methods on the same websites.
Our case study analyzes one indirect fingerprinting technique, Canvas fingerprinting. We use an existing automated detector of this fingerprinting technique to conservatively detect its use on Alexa Top 500 websites that cater to United States consumers, and we examine the privacy policies of the resulting 28 websites. Disclosures of indirect fingerprinting vary in specificity. None described the specific methods with enough granularity to know the website used Canvas fingerprinting. Conversely, many sites did provide enough detail about usage of direct fingerprinting methods to allow a website visitor to reliably detect and block those techniques.
We conclude that indirect fingerprinting methods are often difficult to detect and are not identified with specificity in privacy policies. This makes indirect fingerprinting more difficult to block, and therefore risks disturbing the tentative armistice between individuals and websites currently in place for direct fingerprinting. This paper illustrates differences in fingerprinting approaches, and explains why technologists, technology lawyers, and policymakers need to appreciate the challenges of indirect fingerprinting.

[133]
Title: Enabling and Exploiting Partition-Level Parallelism (PALP) in Phase Change Memories
Comments: 13 pages, 16 figures, 71 references. Published at ACM CASES 2019
Subjects: Hardware Architecture (cs.AR); Emerging Technologies (cs.ET)

Phase-change memory (PCM) devices have multiple banks to serve memory requests in parallel. Unfortunately, if two requests go to the same bank, they have to be served one after another, leading to lower system performance. We observe that a modern PCM bank is implemented as a collection of partitions that operate mostly independently while sharing a few global peripheral structures, which include the sense amplifiers (to read) and the write drivers (to write). Based on this observation, we propose PALP, a new mechanism that enables partition-level parallelism within each PCM bank, and exploits such parallelism by using the memory controller's access scheduling decisions. PALP consists of three new contributions. First, we introduce new PCM commands to enable parallelism in a bank's partitions in order to resolve the read-write bank conflicts, with minimal changes needed to PCM logic and its interface. Second, we propose simple circuit modifications that introduce a new operating mode for the write drivers, in addition to their default mode of serving write requests. When configured in this new mode, the write drivers can resolve the read-read bank conflicts, working jointly with the sense amplifiers. Finally, we propose a new access scheduling mechanism in PCM that improves performance by prioritizing those requests that exploit partition-level parallelism over other requests, including the long outstanding ones. While doing so, the memory controller also guarantees starvation-freedom and the PCM's running-average-power-limit (RAPL). We evaluate PALP with workloads from the MiBench and SPEC CPU2017 Benchmark suites. Our results show that PALP reduces average PCM access latency by 23%, and improves average system performance by 28% compared to the state-of-the-art approaches.

[134]
Title: Assessing the Impact of a User-Item Collaborative Attack on Class of Users
Comments: 5 pages, RecSys2019, The 1st Workshop on the Impact of Recommender Systems with ACM RecSys 2019
Subjects: Information Retrieval (cs.IR); Cryptography and Security (cs.CR); Machine Learning (cs.LG)

Collaborative Filtering (CF) models lie at the core of most recommendation systems due to their state-of-the-art accuracy. They are commonly adopted in e-commerce and online services for their impact on sales volume and/or diversity, and their impact on companies' outcome. However, CF models are only as good as the interaction data they work with. As these models rely on outside sources of information, counterfeit data such as user ratings or reviews can be injected by attackers to manipulate the underlying data and alter the impact of resulting recommendations, thus implementing a so-called shilling attack. While previous works have focused on evaluating shilling attack strategies from a global perspective paying particular attention to the effect of the size of attacks and attacker's knowledge, in this work we explore the effectiveness of shilling attacks under novel aspects. First, we investigate the effect of attack strategies crafted on a target user in order to push the recommendation of a low-ranking item to a higher position, referred to as user-item attack. Second, we evaluate the effectiveness of attacks in altering the impact of different CF models by contemplating the class of the target user, from the perspective of the richness of her profile (i.e., cold v.s. warm user). Finally, similar to previous work we contemplate the size of attack (i.e., the amount of fake profiles injected) in examining their success. The results of experiments on two widely used datasets in business and movie domains, namely Yelp and MovieLens, suggest that warm and cold users exhibit contrasting behaviors in datasets with different characteristics.

[135]
Title: A Multi-level Clustering Approach for Anonymizing Large-Scale Physical Activity Data
Authors: Pooja Parameshwarappa (1), Zhiyuan Chen (1), Gunes Koru (1) ((1) University of Maryland Baltimore County)
Subjects: Cryptography and Security (cs.CR)

Publishing physical activity data can facilitate reproducible health-care research in several areas such as population health management, behavioral health research, and management of chronic health problems. However, publishing such data also brings high privacy risks related to re-identification which makes anonymization necessary. One of the challenges in anonymizing physical activity data collected periodically is its sequential nature. The existing anonymization techniques work sufficiently for cross-sectional data but have high computational costs when applied directly to sequential data. This paper presents an effective anonymization approach, Multi-level Clustering based anonymization to anonymize physical activity data. Compared with the conventional methods, the proposed approach improves time complexity by reducing the clustering time drastically. While doing so, it preserves the utility as much as the conventional approaches.

[136]
Title: QCNN: Quantile Convolutional Neural Network
Subjects: Machine Learning (cs.LG); Computational Finance (q-fin.CP); Machine Learning (stat.ML)

A dilated causal one-dimensional convolutional neural network architecture is proposed for quantile regression. The model can forecast any arbitrary quantile, and it can be trained jointly on multiple similar time series. An application to Value at Risk forecasting shows that QCNN outperforms linear quantile regression and constant quantile estimates.

[137]
Title: Minimal residual multistep methods for large stiff non-autonomous linear problems
Authors: Boris Faleichik
Subjects: Numerical Analysis (math.NA)

The purpose of this work is to introduce a new idea of how to avoid the factorization of large matrices during the solution of stiff systems of ODEs. Starting from the general form of an explicit linear multistep method we suggest to adaptively choose its coefficients on each integration step in order to minimize the norm of the residual of an implicit BDF formula. Thereby we reduce the number of unknowns on each step from $n$ to $O(1)$, where $n$ is the dimension of the ODE system. We call this type of methods Minimal Residual Multistep (MRMS) methods. In the case of linear non-autonomous problem, besides the evaluations of the right-hand side of ODE, the resulting numerical scheme additionally requires one solution of a linear least-squares problem with a thin matrix per step. We show that the order of the method and its zero-stability properties coincide with those of the used underlying BDF formula. For the simplest analog of the implicit Euler method the properties of linear stability are investigated. Though the classical absolute stability analysis is not fully relevant to the MRMS methods, it is shown that this one-step method is applicable in stiff case. In the numerical experiment section we consider the fixed-step integration of a two-dimensional non-autonomous heat equation using the MRMS methods and their classical BDF counterparts. The starting values are taken from a preset slowly-varying exact solution. The comparison showed that both methods give similar numerical solutions, but in the case of large systems the MRMS methods are faster, and their advantage considerably increases with the growth of dimension. Python code with the experimantal code can be downloaded from the GitHub repository https://github.com/bfaleichik/mrms.

[138]
Title: MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
Comments: Accepted at the 25th Annual International Conference on Mobile Computing and Networking (MobiCom), 2019
Subjects: Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)

In recent years, convolutional networks have demonstrated unprecedented performance in the image restoration task of super-resolution (SR). SR entails the upscaling of a single low-resolution image in order to meet application-specific image quality demands and plays a key role in mobile devices. To comply with privacy regulations and reduce the overhead of cloud computing, executing SR models locally on-device constitutes a key alternative approach. Nevertheless, the excessive compute and memory requirements of SR workloads pose a challenge in mapping SR networks on resource-constrained mobile platforms. This work presents MobiSR, a novel framework for performing efficient super-resolution on-device. Given a target mobile platform, the proposed framework considers popular model compression techniques and traverses the design space to reach the highest performing trade-off between image quality and processing speed. At run time, a novel scheduler dispatches incoming image patches to the appropriate model-engine pair based on the patch's estimated upscaling difficulty in order to meet the required image quality with minimum processing latency. Quantitative evaluation shows that the proposed framework yields on-device SR designs that achieve an average speedup of 2.13x over highly-optimized parallel difficulty-unaware mappings and 4.79x over highly-optimized single compute engine implementations.

[139]
Title: Consistent Feature Construction with Constrained Genetic Programming for Experimental Physics
Comments: Accepted in this version to CEC 2019
Journal-ref: Proceedings of 2019 IEEE Congress on Evolutionary Computation (CEC), Wellington, New Zealand, 2019, pp. 1650-1658
Subjects: Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG); Machine Learning (stat.ML)

A good feature representation is a determinant factor to achieve high performance for many machine learning algorithms in terms of classification. This is especially true for techniques that do not build complex internal representations of data (e.g. decision trees, in contrast to deep neural networks). To transform the feature space, feature construction techniques build new high-level features from the original ones. Among these techniques, Genetic Programming is a good candidate to provide interpretable features required for data analysis in high energy physics. Classically, original features or higher-level features based on physics first principles are used as inputs for training. However, physicists would benefit from an automatic and interpretable feature construction for the classification of particle collision events.
Our main contribution consists in combining different aspects of Genetic Programming and applying them to feature construction for experimental physics. In particular, to be applicable to physics, dimensional consistency is enforced using grammars.
Results of experiments on three physics datasets show that the constructed features can bring a significant gain to the classification accuracy. To the best of our knowledge, it is the first time a method is proposed for interpretable feature construction with units of measurement, and that experts in high-energy physics validate the overall approach as well as the interpretability of the built features.

[140]
Title: Evolutionary Computation, Optimization and Learning Algorithms for Data Science
Subjects: Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG); Machine Learning (stat.ML)

A large number of engineering, science and computational problems have yet to be solved in a computationally efficient way. One of the emerging challenges is how evolving technologies grow towards autonomy and intelligent decision making. This leads to collection of large amounts of data from various sensing and measurement technologies, e.g., cameras, smart phones, health sensors, smart electricity meters, and environment sensors. Hence, it is imperative to develop efficient algorithms for generation, analysis, classification, and illustration of data. Meanwhile, data is structured purposefully through different representations, such as large-scale networks and graphs. We focus on data science as a crucial area, specifically focusing on a curse of dimensionality (CoD) which is due to the large amount of generated/sensed/collected data. This motivates researchers to think about optimization and to apply nature-inspired algorithms, such as evolutionary algorithms (EAs) to solve optimization problems. Although these algorithms look un-deterministic, they are robust enough to reach an optimal solution. Researchers do not adopt evolutionary algorithms unless they face a problem which is suffering from placement in local optimal solution, rather than global optimal solution. In this chapter, we first develop a clear and formal definition of the CoD problem, next we focus on feature extraction techniques and categories, then we provide a general overview of meta-heuristic algorithms, its terminology, and desirable properties of evolutionary algorithms.

[141]
Title: Evolution of Ant Colony Optimization Algorithm -- A Brief Literature Review
Subjects: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)

Ant Colony Optimization (ACO) is a metaheuristic proposed by Marco Dorigo in 1991 based on behavior of biological ants. Pheromone laying and selection of shortest route with the help of pheromone inspired development of first ACO algorithm. Since, presentation of first such algorithm, many researchers have worked and published their research in this field. Though initial results were not so promising but recent developments have made this metaheuristic a significant algorithm in Swarm Intelligence. This research presents a brief overview of recent developments carried out in ACO algorithms in terms of both applications and algorithmic developments. For application developments, multi-objective optimization, continuous optimization and time-varying NP-hard problems have been presented. While to review articles based on algorithmic development, hybridization and parallel architectures have been investigated.

[142]
Title: Improving the Results of De novo Peptide Identification via Tandem Mass Spectrometry Using a Genetic Programming-based Scoring Function for Re-ranking Peptide-Spectrum Matches
Comments: 13 pages, conference paper, containing 2 figures
Subjects: Neural and Evolutionary Computing (cs.NE); Quantitative Methods (q-bio.QM)

De novo peptide sequencing algorithms have been widely used in proteomics to analyse tandem mass spectra (MS/MS) and assign them to peptides, but quality-control methods to evaluate the confidence of de novo peptide sequencing are lagging behind. A fundamental part of a quality-control method is the scoring function used to evaluate the quality of peptide-spectrum matches (PSMs). Here, we propose a genetic programming (GP) based method, called GP-PSM, to learn a PSM scoring function for improving the rate of confident peptide identification from MS/MS data. The GP method learns from thousands of MS/MS spectra. Important characteristics about goodness of the matches are extracted from the learning set and incorporated into the GP scoring functions. We compare GP-PSM with two methods including Support Vector Regression (SVR) and Random Forest (RF). The GP method along with RF and SVR, each is used for post-processing the results of peptide identification by PEAKS, a commonly used de novo sequencing method. The results show that GP-PSM outperforms RF and SVR and discriminates accurately between correct and incorrect PSMs. It correctly assigns peptides to 10% more spectra on an evaluation dataset containing 120 MS/MS spectra and decreases the false positive rate (FPR) of peptide identification.

[143]
Title: A Fast and Efficient Stochastic Opposition-Based Learning for Differential Evolution in Numerical Optimization
Subjects: Neural and Evolutionary Computing (cs.NE)

A new variant of stochastic opposition-based learning (OBL) is proposed in this paper. OBL is a relatively new machine learning concept, which consists of simultaneously calculating an original solution and its opposite to accelerate the convergence of soft computing algorithms. Recently a new opposition-based differential evolution (ODE) variant called BetaCODE was proposed as a combination of differential evolution and a new stochastic OBL variant called BetaCOBL. BetaCOBL is capable of flexibly adjusting the probability density functions used to calculate opposite solutions, generating more diverse opposite solutions, and preventing the waste of fitness evaluations. While it has shown outstanding performance compared to several state-of-the-art OBL variants, BetaCOBL is challenging with more complex problems because of its high computational cost. Besides, as it assumes that the decision variables are independent, there is a limitation in the search for decent opposite solutions on inseparable problems. In this paper, we propose an improved stochastic OBL variant that mitigates all the limitations of BetaCOBL. The proposed algorithm called iBetaCOBL reduces the computational cost from $O(NP^{2} \cdot D)$ to $O(NP \cdot D)$ ($NP$ and $D$ stand for population size and dimension, respectively) using a linear time diversity measure. In addition, iBetaCOBL preserves the strongly dependent decision variables that are adjacent to each other using the multiple exponential crossover. The results of the performance evaluations on a set of 58 test functions show that iBetaCODE finds more accurate solutions than ten state-of-the-art ODE variants including BetaCODE. Additionally, we applied iBetaCOBL to two state-of-the-art DE variants, and as in the previous results, iBetaCOBL based variants exhibit significantly improved performance.

[144]
Title: Efficient training and design of photonic neural network through neuroevolution
Subjects: Neural and Evolutionary Computing (cs.NE); Optics (physics.optics)

Recently, optical neural networks (ONNs) integrated in photonic chips has received extensive attention because they are expected to implement the same pattern recognition tasks in the electronic platforms with high efficiency and low power consumption. However, the current lack of various learning algorithms to train the ONNs obstructs their further development. In this article, we propose a novel learning strategy based on neuroevolution to design and train the ONNs. Two typical neuroevolution algorithms are used to determine the hyper-parameters of the ONNs and to optimize the weights (phase shifters) in the connections. In order to demonstrate the effectiveness of the training algorithms, the trained ONNs are applied in the classification tasks for iris plants dataset, wine recognition dataset and modulation formats recognition. The calculated results exhibit that the training algorithms based on neuroevolution are competitive with other traditional learning algorithms on both accuracy and stability. Compared with previous works, we introduce an efficient training method for the ONNs and demonstrate their broad application prospects in pattern recognition, reinforcement learning and so on.

[145]
Title: Adaptive Morley FEM for the von Kármán equations with optimal convergence rates
Subjects: Numerical Analysis (math.NA)

The adaptive nonconforming Morley finite element method (FEM) approximates a regular solution to the von K\'{a}rm\'{a}n equations with optimal convergence rates for sufficiently fine triangulations and small bulk parameter in the D\"orfler marking. This follows from the general axiomatic framework with the key arguments of stability, reduction, discrete reliability, and quasiorthogonality of an explicit residual-based error estimator. Particular attention is on the nonlinearity and the piecewise Sobolev embeddings required in the resulting trilinear form in the weak formulation of the nonconforming discretisation. The discrete reliability follows with a conforming companion for the discrete Morley functions from the medius analysis. The quasiorthogonality also relies on a novel piecewise $H^1$ a~priori error estimate and a careful analysis of the nonlinearity.

[146]
Title: Graph based adaptive evolutionary algorithm for continuous optimization
Journal-ref: OLA conference 2018
Subjects: Neural and Evolutionary Computing (cs.NE); Distributed, Parallel, and Cluster Computing (cs.DC)

he greatest weakness of evolutionary algorithms, widely used today, is the premature convergence due to the loss of population diversity over generations. To overcome this problem, several algorithms have been proposed, such as the Graph-based Evolutionary Algorithm (GEA) \cite{1} which uses graphs to model the structure of the population, but also memetic or differential evolution algorithms \cite{2,3}, or diversity-based ones \cite{4,5} have been designed. These algorithms are based on multi-populations, or often rather focus on the self-tuning parameters, however, they become complex to tune because of their high number of parameters. In this paper, our approach consists of an evolutionary algorithm that allows a dynamic adaptation of the search operators based on a graph in order to limit the loss of diversity and reduce the design complexity.

[147]
Subjects: Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG)

[148]
Title: Testing Robustness Against Unforeseen Adversaries
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)

Considerable work on adversarial defense has studied robustness to a fixed, known family of adversarial distortions, most frequently L_p-bounded distortions. In reality, the specific form of attack will rarely be known and adversaries are free to employ distortions outside of any fixed set. The present work advocates measuring robustness against this much broader range of unforeseen attacks---attacks whose precise form is not known when designing a defense.
We propose a methodology for evaluating a defense against a diverse range of distortion types together with a summary metric UAR that measures the Unforeseen Attack Robustness against a distortion. We construct novel JPEG, Fog, Gabor, and Snow adversarial attacks to simulate unforeseen adversaries and perform a careful study of adversarial robustness against these and existing distortion types. We find that evaluation against existing L_p attacks yields highly correlated information that may not generalize to other attacks and identify a set of 4 attacks that yields more diverse information. We further find that adversarial training against either one or multiple distortions, including our novel ones, does not confer robustness to unforeseen distortions. These results underscore the need to study robustness against unforeseen distortions and provide a starting point for doing so.

[149]
Title: Knowledge transfer in deep block-modular neural networks
Subjects: Neural and Evolutionary Computing (cs.NE)

Although deep neural networks (DNNs) have demonstrated impressive results during the last decade, they remain highly specialized tools, which are trained -- often from scratch -- to solve each particular task. The human brain, in contrast, significantly re-uses existing capacities when learning to solve new tasks. In the current study we explore a block-modular architecture for DNNs, which allows parts of the existing network to be re-used to solve a new task without a decrease in performance when solving the original task. We show that networks with such architectures can outperform networks trained from scratch, or perform comparably, while having to learn nearly 10 times fewer weights than the networks trained from scratch.

[150]
Title: Exploiting a Stimuli Encoding Scheme of Spiking Neural Networks for Stream Learning
Subjects: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Stream data processing has gained progressive momentum with the arriving of new stream applications and big data scenarios. One of the most promising techniques in stream learning is the Spiking Neural Network, and some of them use an interesting population encoding scheme to transform the incoming stimuli into spikes. This study sheds lights on the key issue of this encoding scheme, the Gaussian receptive fields, and focuses on applying them as a pre-processing technique to any dataset in order to gain representativeness, and to boost the predictive performance of the stream learning methods. Experiments with synthetic and real data sets are presented, and lead to confirm that our approach can be applied successfully as a general pre-processing technique in many real cases.

[151]
Title: Spiking Neural Networks and Online Learning: An Overview and Perspectives
Subjects: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Applications that generate huge amounts of data in the form of fast streams are becoming increasingly prevalent, being therefore necessary to learn in an online manner. These conditions usually impose memory and processing time restrictions, and they often turn into evolving environments where a change may affect the input data distribution. Such a change causes that predictive models trained over these stream data become obsolete and do not adapt suitably to new distributions. Specially in these non-stationary scenarios, there is a pressing need for new algorithms that adapt to these changes as fast as possible, while maintaining good performance scores. Unfortunately, most off-the-shelf classification models need to be retrained if they are used in changing environments, and fail to scale properly. Spiking Neural Networks have revealed themselves as one of the most successful approaches to model the behavior and learning potential of the brain, and exploit them to undertake practical online learning tasks. Besides, some specific flavors of Spiking Neural Networks can overcome the necessity of retraining after a drift occurs. This work intends to merge both fields by serving as a comprehensive overview, motivating further developments that embrace Spiking Neural Networks for online learning scenarios, and being a friendly entry point for non-experts.

[152]
Title: Comparing reliability of grid-based Quality-Diversity algorithms using artificial landscapes
Authors: Leo Cazenille
Journal-ref: Genetic and Evolutionary Computation Conference Companion (GECCO '19 Companion), July 13--17, 2019, Prague, Czech Republic
Subjects: Neural and Evolutionary Computing (cs.NE)

Quality-Diversity (QD) algorithms are a recent type of optimisation methods that search for a collection of both diverse and high performing solutions. They can be used to effectively explore a target problem according to features defined by the user. However, the field of QD still does not possess extensive methodologies and reference benchmarks to compare these algorithms. We propose a simple benchmark to compare the reliability of QD algorithms by optimising the Rastrigin function, an artificial landscape function often used to test global optimisation methods.

[153]
Title: Reservoir-size dependent learning in analogue neural networks
Subjects: Neural and Evolutionary Computing (cs.NE); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Machine Learning (stat.ML)

The implementation of artificial neural networks in hardware substrates is a major interdisciplinary enterprise. Well suited candidates for physical implementations must combine nonlinear neurons with dedicated and efficient hardware solutions for both connectivity and training. Reservoir computing addresses the problems related with the network connectivity and training in an elegant and efficient way. However, important questions regarding impact of reservoir size and learning routines on the convergence-speed during learning remain unaddressed. Here, we study in detail the learning process of a recently demonstrated photonic neural network based on a reservoir. We use a greedy algorithm to train our neural network for the task of chaotic signals prediction and analyze the learning-error landscape. Our results unveil fundamental properties of the system's optimization hyperspace. Particularly, we determine the convergence speed of learning as a function of reservoir size and find exceptional, close to linear scaling. This linear dependence, together with our parallel diffractive coupling, represent optimal scaling conditions for our photonic neural network scheme.

[154]
Title: Genetic Algorithm for the 0/1 Multidimensional Knapsack Problem
Authors: Shalin Shah
Subjects: Neural and Evolutionary Computing (cs.NE); Optimization and Control (math.OC)

The 0/1 multidimensional knapsack problem is the 0/1 knapsack problem with m constraints which makes it difficult to solve using traditional methods like dynamic programming or branch and bound algorithms. We present a genetic algorithm for the multidimensional knapsack problem with Java code that is able to solve publicly available instances in a very short computational duration. Our algorithm uses iteratively computed Lagrangian multipliers as constraint weights to augment the greedy algorithm for the multidimensional knapsack problem and uses that information in a greedy crossover in a genetic algorithm. The algorithm uses several other hyperparameters which can be set in the code to control convergence. Our algorithm improves upon the algorithm by Chu and Beasley in that it converges to optimum or near optimum solutions much faster.

[155]
Title: WikiCREM: A Large Unsupervised Corpus for Coreference Resolution
Comments: Accepted to the EMNLP 2019 conference
Subjects: Computation and Language (cs.CL)

Pronoun resolution is a major area of natural language understanding. However, large-scale training sets are still scarce, since manually labelling data is costly. In this work, we introduce WikiCREM (Wikipedia CoREferences Masked) a large-scale, yet accurate dataset of pronoun disambiguation instances. We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset. We compare a series of models on a collection of diverse and challenging coreference resolution problems, where we match or outperform previous state-of-the-art approaches on 6 out of 7 datasets, such as GAP, DPR, WNLI, PDP, WinoBias, and WinoGender. We release our model to be used off-the-shelf for solving pronoun disambiguation.

[156]
Title: Refactoring Neural Networks for Verification
Subjects: Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG); Software Engineering (cs.SE)

Deep neural networks (DNN) are growing in capability and applicability. Their effectiveness has led to their use in safety critical and autonomous systems, yet there is a dearth of cost-effective methods available for reasoning about the behavior of a DNN. In this paper, we seek to expand the applicability and scalability of existing DNN verification techniques through DNN refactoring. A DNN refactoring defines (a) the transformation of the DNN's architecture, i.e., the number and size of its layers, and (b) the distillation of the learned relationships between the input features and function outputs of the original to train the transformed network. Unlike with traditional code refactoring, DNN refactoring does not guarantee functional equivalence of the two networks, but rather it aims to preserve the accuracy of the original network while producing a simpler network that is amenable to more efficient property verification. We present an automated framework for DNN refactoring, and demonstrate its potential effectiveness through three case studies on networks used in autonomous systems.

[157]
Title: MuSHR: A Low-Cost, Open-Source Robotic Racecar for Education and Research
Subjects: Robotics (cs.RO)

We present MuSHR, the Multi-agent System for non-Holonomic Racing. MuSHR is a low-cost, open-source robotic racecar platform for education and research, developed by the Personal Robotics Lab in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. MuSHR aspires to contribute towards democratizing the field of robotics as a low-cost platform that can be built and deployed by following detailed, open documentation and do-it-yourself tutorials. A set of demos and lab assignments developed for the Mobile Robots course at the University of Washington provide guided, hands-on experience with the platform, and milestones for further development. MuSHR is a valuable asset for academic research labs, robotics instructors, and robotics enthusiasts.

### Cross-lists for Thu, 22 Aug 19

[158]  arXiv:1908.07516 (cross-list from eess.IV) [pdf, other]
Title: Direct Neural Network 3D Image Reconstruction of Radon Encoded Data
Comments: Submitted to the Journal of Medical Imaging
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Medical Physics (physics.med-ph)

Neural network image reconstruction directly from measurement data is a growing field of research, but until now has been limited to producing small (e.g. 128x128) 2D images by the large memory requirements of the previously suggested networks. In order to facilitate further research with direct reconstruction, we developed a more efficient network capable of 3D reconstruction of Radon encoded data with a relatively large image matrix (e.g. 400x400). Our proposed network is able to produce image quality comparable to the benchmark Ordered Subsets Expectation Maximization (OSEM) algorithm. We address the most memory intensive aspect of transforming the data from sinogram space to image space through a specially designed Radon inversion layer. We insert this layer between an initial network segment designed to encode the sinogram input and an output segment designed to refine and scale the initial image estimate to produce the final image. We demonstrate 3D reconstructions comparable to OSEM for 1, 4, 8 and 16 slices with no modifications to the network's architecture, capacity or hyper-parameters on a data set of simulated PET whole-body scans. When batch operations are considered, this network can reconstruct an entire PET whole-body volume in a single pass or about one second. Although results in this paper are on PET data, the proposed methods would be equally applicable to X-ray CT or any other Radon encoded measurement data.

[159]  arXiv:1908.07521 (cross-list from stat.OT) [pdf, other]
Title: Distributed Hypothesis Testing over a Noisy Channel: Error-exponents Trade-off
Subjects: Other Statistics (stat.OT); Information Theory (cs.IT)

A distributed hypothesis testing problem with two parties, one referred to as the observer and the other as the detector, is considered. The observer observes a discrete memoryless source and communicates its observations to the detector over a discrete memoryless noisy channel. The detector observes a side-information correlated with the observer's observations, and performs a binary hypothesis test on the joint probability distribution of its own observations with that of the observer. With the objective of characterizing the performance of the hypothesis test, we obtain two inner bounds on the trade-off between the exponents of the type I and type II error probabilities. The first inner bound is obtained using a combination of a type-based quantize-bin scheme and Borade et al.'s unequal error protection scheme, while the second inner bound is established using a type-based hybrid coding scheme. These bounds extend the achievability result of Han and Kobayashi obtained for the special case of a rate-limited noiseless channel to a noisy channel. For the special case of testing for the marginal distribution of the observer's observations with no side-information at the detector, we establish a single-letter characterization of the optimal trade-off between the type I and type II error-exponents. Our results imply that a separation holds in this case, in the sense that the optimal trade-off between the error-exponents is achieved by a scheme that performs independent hypothesis testing and channel coding.

[160]  arXiv:1908.07561 (cross-list from econ.TH) [pdf, ps, other]
Title: New developments in revealed preference theory: decisions under risk, uncertainty, and intertemporal choice
Subjects: Theoretical Economics (econ.TH); Computer Science and Game Theory (cs.GT); Econometrics (econ.EM)

The chapter reviews recent developments in revealed preference theory. It discusses the testable implications of theories of choice that are germane to specific economic environments. The focus is on expected utility in risky environments; subjected expected utility and maxmin expected utility in the presence of uncertainty; and exponentially discounted utility for intertemporal choice. The testable implications of these theories for data on choice from classical linear budget sets are described, and shown to follow a common thread. The theories all imply an inverse relation between prices and quantities, with different qualifications depending on the functional forms in the theory under consideration.

[161]  arXiv:1908.07568 (cross-list from eess.SP) [pdf]
Title: Power-Efficient Resource Allocation in Massive MIMO Aided Cloud RANs
Subjects: Signal Processing (eess.SP); Information Theory (cs.IT)

This paper considers the power-efficient resource allocation problem in a cloud radio access network (C-RAN). The C-RAN architecture consists of a set of base-band units (BBUs) which are connected to a set of radio remote heads (RRHs) equipped with massive multiple input multiple output (MIMO), via fronthaul links with limited capacity. We formulate the power-efficient optimization problem in C-RANs as a joint resource allocation problem in order to jointly allocate the RRH and transmit power to each user, and fronthaul links and BBUs assign to active RRHs while satisfying the minimum required rate of each user. To solve this non-convex optimization problem we suggest iterative algorithm with two-step based on the complementary geometric programming (CGP) and the successive convex approximation (SCA). The simulation results indicate that our proposed scheme can significantly reduce the total transmission power by switching off the under-utilized RRHs.

[162]  arXiv:1908.07607 (cross-list from stat.ML) [pdf, other]
Title: Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Computation (stat.CO)

Stochastic Gradient Descent (SGD) methods are prominent for training machine learning and deep learning models. The performance of these techniques depends on their hyperparameter tuning over time and varies for different models and problems. Manual adjustment of hyperparameters is very costly and time-consuming, and even if done correctly, it lacks theoretical justification which inevitably leads to "rule of thumb" settings. In this paper, we propose a generic approach that utilizes the statistics of an unbiased gradient estimator to automatically and simultaneously adjust two paramount hyperparameters: the learning rate and momentum. We deploy the proposed general technique for various SGD methods to train Convolutional Neural Networks (CNN's). The results match the performance of the best settings obtained through an exhaustive search and therefore, removes the need for a tedious manual tuning.

[163]  arXiv:1908.07619 (cross-list from eess.SP) [pdf, other]
Title: Detecting Gas Vapor Leaks Using Uncalibrated Sensors
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG)

Chemical and infra-red sensors generate distinct responses under similar conditions because of sensor drift, noise or resolution errors. In this work, we use different time-series data sets obtained by infra-red and E-nose sensors in order to detect Volatile Organic Compounds (VOCs) and Ammonia vapor leaks. We process time-series sensor signals using deep neural networks (DNN). Three neural network algorithms are utilized for this purpose. Additive neural networks (termed AddNet) are based on a multiplication-devoid operator and consequently exhibit energy-efficiency compared to regular neural networks. The second algorithm uses generative adversarial neural networks so as to expose the classifying neural network to more realistic data points in order to help the classifier network to deliver improved generalization. Finally, we use conventional convolutional neural networks as a baseline method and compare their performance with the two aforementioned deep neural network algorithms in order to evaluate their effectiveness empirically.

[164]  arXiv:1908.07623 (cross-list from eess.IV) [pdf, other]
Title: Joint Motion Estimation and Segmentation from Undersampled Cardiac MR Image
Comments: This work is published at MLMIR 2018: Machine Learning for Medical Image Reconstruction
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Accelerating the acquisition of magnetic resonance imaging (MRI) is a challenging problem, and many works have been proposed to reconstruct images from undersampled k-space data. However, if the main purpose is to extract certain quantitative measures from the images, perfect reconstructions may not always be necessary as long as the images enable the means of extracting the clinically relevant measures. In this paper, we work on jointly predicting cardiac motion estimation and segmentation directly from undersampled data, which are two important steps in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In particular, a unified model consisting of both motion estimation branch and segmentation branch is learned by optimising the two tasks simultaneously. Additional corresponding fully-sampled images are incorporated into the network as a parallel sub-network to enhance and guide the learning during the training process. Experimental results using cardiac MR images from 220 subjects show that the proposed model is robust to undersampled data and is capable of predicting results that are close to that from fully-sampled ones, while bypassing the usual image reconstruction stage.

[165]  arXiv:1908.07636 (cross-list from stat.ML) [pdf, other]
Title: How to gamble with non-stationary $\mathcal{X}$-armed bandits and have no regrets
Authors: Vakeriy Avanesov
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)

In $\mathcal{X}$-armed bandit problem an agent sequentially interacts with environment which yields a reward based on the vector input the agent provides. The agent's goal is to maximise the sum of these rewards across some number of time steps. The problem and its variations have been a subject of numerous studies, suggesting sub-linear and some times optimal strategies. The given paper introduces a novel variation of the problem. We consider an environment, which can abruptly change its behaviour an unknown number of times. To that end we propose a novel strategy and prove it attains sub-linear cumulative regret. Moreover, in case of highly smooth relation between an action and the corresponding reward, the method is nearly optimal. The theoretical result are supported by experimental study.

[166]  arXiv:1908.07656 (cross-list from eess.AS) [pdf]
Title: Survey on Deep Neural Networks in Speech and Vision Systems
Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Sound (cs.SD); Signal Processing (eess.SP); Machine Learning (stat.ML)

This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and development of intelligent vision and speech systems. With availability of vast amounts of sensor data and cloud computing for processing and training of deep neural networks, and with increased sophistication in mobile and embedded technology, the next-generation intelligent systems are poised to revolutionize personal and commercial computing. This survey begins by providing background and evolution of some of the most successful deep learning models for intelligent vision and speech systems to date. An overview of large-scale industrial research and development efforts is provided to emphasize future trends and prospects of intelligent vision and speech systems. Robust and efficient intelligent systems demand low-latency and high fidelity in resource constrained hardware platforms such as mobile devices, robots, and automobiles. Therefore, this survey also provides a summary of key challenges and recent successes in running deep neural networks on hardware-restricted platforms, i.e. within limited memory, battery life, and processing capabilities. Finally, emerging applications of vision and speech across disciplines such as affective computing, intelligent transportation, and precision medicine are discussed. To our knowledge, this paper provides one of the most comprehensive surveys on the latest developments in intelligent vision and speech applications from the perspectives of both software and hardware systems. Many of these emerging technologies using deep neural networks show tremendous promise to revolutionize research and development for future vision and speech systems.

[167]  arXiv:1908.07696 (cross-list from eess.SP) [pdf, other]
Title: First 20 Years of Green Radios
Subjects: Signal Processing (eess.SP); Systems and Control (eess.SY)

[168]  arXiv:1908.07704 (cross-list from eess.IV) [pdf]
Title: Lung segmentation on chest x-ray images in patients with severe abnormal findings using deep learning
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Rationale and objectives: Several studies have evaluated the usefulness of deep learning for lung segmentation using chest x-ray (CXR) images with small- or medium-sized abnormal findings. Here, we built a database including both CXR images with severe abnormalities and experts' lung segmentation results, and aimed to evaluate our network's efficacy in lung segmentation from these images. Materials and Methods: For lung segmentation, CXR images from the Japanese Society of Radiological Technology (JSRT, N = 247) and Montgomery databases (N = 138), were included, and 65 additional images depicting severe abnormalities from a public database were evaluated and annotated by a radiologist, thereby adding lung segmentation results to these images. Baseline U-net was used to segment the lungs in images from the three databases. Subsequently, the U-net network architecture was automatically optimized for lung segmentation from CXR images using Bayesian optimization. Dice similarity coefficient (DSC) was calculated to confirm segmentation. Results: Our results demonstrated that using baseline U-net yielded poorer lung segmentation results in our database than those in the JSRT and Montgomery databases, implying that robust segmentation of lungs may be difficult because of severe abnormalities. The DSC values with baseline U-net for the JSRT, Montgomery and our databases were 0.979, 0.941, and 0.889, respectively, and with optimized U-net, 0.976, 0.973, and 0.932, respectively. Conclusion: For robust lung segmentation, the U-net architecture was optimized via Bayesian optimization, and our results demonstrate that the optimized U-net was more robust than baseline U-net in lung segmentation from CXR images with large-sized abnormalities.

[169]  arXiv:1908.07726 (cross-list from eess.IV) [pdf, other]
Title: Automated Multi-sequence Cardiac MRI Segmentation Using Supervised Domain Adaptation
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Left ventricle segmentation and morphological assessment are essential for improving diagnosis and our understanding of cardiomyopathy, which in turn is imperative for reducing risk of myocardial infarctions in patients. Convolutional neural network (CNN) based methods for cardiac magnetic resonance (CMR) image segmentation rely on supervision with pixel-level annotations, and may not generalize well to images from a different domain. These methods are typically sensitive to variations in imaging protocols and data acquisition. Since annotating multi-sequence CMR images is tedious and subject to inter- and intra-observer variations, developing methods that can automatically adapt from one domain to the target domain is of great interest. In this paper, we propose an approach for domain adaptation in multi-sequence CMR segmentation task using transfer learning that combines multi-source image information. We first train an encoder-decoder CNN on T2-weighted and balanced-Steady State Free Precession (bSSFP) MR images with pixel-level annotation and fine-tune the same network with a limited number of Late Gadolinium Enhanced-MR (LGE-MR) subjects, to adapt the domain features. The domain-adapted network was trained with just four LGE-MR training samples and obtained an average Dice score of $\sim$85.0\% on the test set comprises of 40 LGE-MR subjects. The proposed method significantly outperformed a network without adaptation trained from scratch on the same set of LGE-MR training data.

[170]  arXiv:1908.07736 (cross-list from eess.IV) [pdf, other]
Title: Adaptive Segmentation of Knee Radiographs for Selecting the Optimal ROI in Texture Analysis
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

The purposes of this study were to investigate: 1) the effect of placement of region-of-interest (ROI) for texture analysis of subchondral bone in knee radiographs, and 2) the ability of several texture descriptors to distinguish between the knees with and without radiographic osteoarthritis (OA). Bilateral posterior-anterior knee radiographs were analyzed from the baseline of OAI and MOST datasets. A fully automatic method to locate the most informative region from subchondral bone using adaptive segmentation was developed. We used an oversegmentation strategy for partitioning knee images into the compact regions that follow natural texture boundaries. LBP, Fractal Dimension (FD), Haralick features, Shannon entropy, and HOG methods were computed within the standard ROI and within the proposed adaptive ROIs. Subsequently, we built logistic regression models to identify and compare the performances of each texture descriptor and each ROI placement method using 5-fold cross validation setting. Importantly, we also investigated the generalizability of our approach by training the models on OAI and testing them on MOST dataset.We used area under the receiver operating characteristic (ROC) curve (AUC) and average precision (AP) obtained from the precision-recall (PR) curve to compare the results. We found that the adaptive ROI improves the classification performance (OA vs. non-OA) over the commonly used standard ROI (up to 9% percent increase in AUC). We also observed that, from all texture parameters, LBP yielded the best performance in all settings with the best AUC of 0.840 [0.825, 0.852] and associated AP of 0.804 [0.786, 0.820]. Compared to the current state-of-the-art approaches, our results suggest that the proposed adaptive ROI approach in texture analysis of subchondral bone can increase the diagnostic performance for detecting the presence of radiographic OA.

[171]  arXiv:1908.07765 (cross-list from eess.IV) [pdf]
Title: Dataset Growth in Medical Image Analysis Research
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

Medical image analysis studies usually require medical image datasets for training, testing and validation of algorithms. The need is underscored by the deep learning revolution and the dominance of machine learning in recent medical image analysis research. Nevertheless, due to ethical and legal constraints, commercial conflicts and the dependence on busy medical professionals, medical image analysis researchers have been described as "data starved". Due to the lack of objective criteria for sufficiency of dataset size, the research community implicitly sets ad-hoc standards by means of the peer review process. We hypothesize that peer review requires researchers to report the use of ever-increasing datasets as one condition for acceptance of their work to reputable publication venues. To test this hypothesis, we scanned the proceedings of the eminent MICCAI (Medical Image Computing and Computer-Assisted Intervention) conferences from 2011 to 2018. From a total of 2136 articles, we focused on 907 papers involving human datasets of MRI (Magnetic Resonance Imaging), CT (Computed Tomography) and fMRI (functional MRI) images. For each modality, for each of the years 2011-2018 we calculated the average, geometric mean and median number of human subjects used in that year's MICCAI articles. The results corroborate the dataset growth hypothesis. Specifically, the annual median dataset size in MICCAI articles has grown roughly 3-10 times from 2011 to 2018, depending on the imaging modality. Statistical analysis further supports the dataset growth hypothesis and reveals exponential growth of the geometric mean dataset size, with annual growth of about 21% for MRI, 24% for CT and 31% for fMRI. In slight analogy to Moore's law, the results can provide guidance about trends in the expectations of the medical image analysis community regarding dataset size.

[172]  arXiv:1908.07805 (cross-list from stat.AP) [pdf, other]
Title: Importance of spatial predictor variable selection in machine learning applications -- Moving from data reproduction to spatial prediction
Comments: under review in Ecological Modelling
Subjects: Applications (stat.AP); Machine Learning (cs.LG); Machine Learning (stat.ML)

Machine learning algorithms find frequent application in spatial prediction of biotic and abiotic environmental variables. However, the characteristics of spatial data, especially spatial autocorrelation, are widely ignored. We hypothesize that this is problematic and results in models that can reproduce training data but are unable to make spatial predictions beyond the locations of the training samples. We assume that not only spatial validation strategies but also spatial variable selection is essential for reliable spatial predictions. We introduce two case studies that use remote sensing to predict land cover and the leaf area index for the "Marburg Open Forest", an open research and education site of Marburg University, Germany. We use the machine learning algorithm Random Forests to train models using non-spatial and spatial cross-validation strategies to understand how spatial variable selection affects the predictions. Our findings confirm that spatial cross-validation is essential in preventing overoptimistic model performance. We further show that highly autocorrelated predictors (such as geolocation variables, e.g. latitude, longitude) can lead to considerable overfitting and result in models that can reproduce the training data but fail in making spatial predictions. The problem becomes apparent in the visual assessment of the spatial predictions that show clear artefacts that can be traced back to a misinterpretation of the spatially autocorrelated predictors by the algorithm. Spatial variable selection could automatically detect and remove such variables that lead to overfitting, resulting in reliable spatial prediction patterns and improved statistical spatial model performance. We conclude that in addition to spatial validation, a spatial variable selection must be considered in spatial predictions of ecological data to produce reliable predictions.

[173]  arXiv:1908.07834 (cross-list from eess.SP) [pdf, other]
Title: Implementation of a Low-Cost Flight Tracking System for High-Altitude Ballooning
Subjects: Signal Processing (eess.SP); Systems and Control (eess.SY)

High altitude balloons (HABs) are typically tracked via GPS data sent via real-time radio-based communication systems such as the Automated Packet Reporting System (APRS). Prefabricated APRS-compatible tracker modules have made it trivial to transmit GPS coordinates and payload parameters in compliance with the requisite AX.25 protocol. However, in order to receive and track APRS signals, conventional methodologies call for the use of a Very High Frequency (VHF) receiver to demodulate signals transmitted on the 440/144 MHz APRS frequencies, along with a compatible antenna and custom methodology for visualizing the HAB's location on a map. The entire assembly is typically costly, cumbersome, and may require an internet connection in order to obtain real-time visualization of the HAB's location. This paper describes a low-cost, handheld system based on open-source software that operates independently of an internet connection. The miniaturized system is suited to tracking done either from a vehicle or on foot, and is cost-effective enough to be within the means of nearly any HAB user. The paper also discusses preliminary test results and further applications.

[174]  arXiv:1908.07841 (cross-list from physics.geo-ph) [pdf, other]
Title: Ranking Viscous Finger Simulations to an Acquired Ground Truth with Topology-aware Matchings
Subjects: Geophysics (physics.geo-ph); Computational Geometry (cs.CG); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)

This application paper presents a novel framework based on topological data analysis for the automatic evaluation and ranking of viscous finger simulation runs in an ensemble with respect to a reference acquisition. Individual fingers in a given time-step are associated with critical point pairs in the distance field to the injection point, forming persistence diagrams. Different metrics, based on optimal transport, for comparing time-varying persistence diagrams in this specific applicative case are introduced. We evaluate the relevance of the rankings obtained with these metrics, both qualitatively thanks to a lightweight web visual interface, and quantitatively by studying the deviation from a reference ranking suggested by experts. Extensive experiments show the quantitative superiority of our approach compared to traditional alternatives. Our web interface allows experts to conveniently explore the produced rankings. We show a complete viscous fingering case study demonstrating the utility of our approach in the context of porous media fluid flow, where our framework can be used to automatically discard physically-irrelevant simulation runs from the ensemble and rank the most plausible ones. We document an in-situ implementation to lighten I/O and performance constraints arising in the context of parametric studies.

[175]  arXiv:1908.07849 (cross-list from physics.geo-ph) [pdf, other]
Title: Semi-supervised Sequence Modeling for Elastic Impedance Inversion
Comments: A manuscript in Interpretation. arXiv admin note: text overlap with arXiv:1905.13412
Subjects: Geophysics (physics.geo-ph); Machine Learning (cs.LG); Signal Processing (eess.SP); Machine Learning (stat.ML)

Recent applications of machine learning algorithms in the seismic domain have shown great potential in different areas such as seismic inversion and interpretation. However, such algorithms rarely enforce geophysical constraints - the lack of which might lead to undesirable results. To overcome this issue, we have developed a semi-supervised sequence modeling framework based on recurrent neural networks for elastic impedance inversion from multi-angle seismic data. Specifically, seismic traces and elastic impedance (EI) traces are modeled as a time series. Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for EI. The proposed workflow uses well-log data to guide the inversion. In addition, it uses seismic forward modeling to regularize the training and to serve as a geophysical constraint for the inversion. The proposed workflow achieves an average correlation of 98% between the estimated and target EI using 10 well logs for training on a synthetic data set.

[176]  arXiv:1908.07925 (cross-list from math.OC) [pdf, ps, other]
Title: Stability of the linear complementarity problem properties under interval uncertainty
Subjects: Optimization and Control (math.OC); Numerical Analysis (math.NA)

We consider the linear complementarity problem with uncertain data modeled by intervals, representing the range of possible values. Many properties of the linear complementarity problem (such as solvability, uniqueness, convexity, finite number of solutions etc.) are reflected by the properties of the constraint matrix. In order that the problem has desired properties even in the uncertain environment, we have to be able to check them for all possible realizations of interval data. This leads us to the robust properties of interval matrices. In particular, we will discuss $S$-matrix, $Z$-matrix, copositivity, semimonotonicity, column sufficiency, principal nondegeneracy, $R_0$-matrix and $R$-matrix. We characterize the robust properties and also suggest efficiently recognizable subclasses.

[177]  arXiv:1908.07926 (cross-list from eess.IV) [pdf, other]
Title: TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

[178]  arXiv:1908.07934 (cross-list from eess.SP) [pdf, other]
Title: Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback
Subjects: Signal Processing (eess.SP); Machine Learning (cs.LG)

In multiple-input multiple-output (MIMO) systems, it is crucial of utilizing the available channel state information (CSI) at the transmitter for precoding to improve the performance of frequency division duplex (FDD) networks. One of the mainchallenges is to compress a large amount of CSI in CSI feedback transmission in massive MIMO systems. In this paper, we propose a deep learning (DL)-based approach that uses a deep recurrent neural network (RNN) to learn temporal correlation and adopts depthwise separable convolution to shrink the model. The feature extraction module is also elaborately devised by studyingdecoupled spatio-temporal feature representations in different structures. Experimental results demonstrate that the proposed approach outperforms existing DL-based methods in terms of recovery quality and accuracy, which can also achieve remarkable robustness at low compression ratio (CR).

[179]  arXiv:1908.07951 (cross-list from eess.SP) [pdf]
Title: Secure practical indoor optical wireless communications using quantum key distribution
Subjects: Signal Processing (eess.SP); Networking and Internet Architecture (cs.NI)

Quantum Key Distribution (QKD) can guarantee security for practical indoor optical wireless environments. The key challenges are to mitigate artificial lighting and ambient light at the receiver. A new spectral region for QKD is proposed and an ideal QKD link model is simulated with experimental ambient light power measurements. Simulation, modelling, and analysis indicates that the carbon dioxide and water absorption band (1370 nm) is a new wavelength region for QKD operation in indoor optical wireless environments. For a feasible QKD link, approximately 20 dB of signal to noise ratio (SNR) is required and a maximum quantum bit error rate (QBER) of 11% when using the BB84 protocol. Links in the new spectral region with a FOV of several degrees are feasible, depending on available components.

[180]  arXiv:1908.07957 (cross-list from q-bio.NC) [pdf, other]
Title: DISCo for the CIA: Deep learning, Instance Segmentation, and Correlations for Calcium Imaging Analysis
Subjects: Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG); Image and Video Processing (eess.IV)

Calcium imaging is one of the most important tools in neurophysiology as it enables the observation of neuronal activity for hundreds of cells in parallel and at single-cell resolution. In order to use the data gained with calcium imaging, it is necessary to extract individual cells and their activity from the recordings. Although many sophisticated methods have been proposed, the cell extraction from calcium imaging data can still be prohibitively laborious and require manual annotation and correction. We present DISCo, a novel approach for the cell segmentation in Calcium Imaging Analysis (CIA) that combines the advantages of Deep learning with a state-of-the-art Instance Segmentation algorithm and uses temporal information from the recordings in a computationally efficient way by computing Correlations between pixels.

[181]  arXiv:1908.07967 (cross-list from eess.SP) [pdf, other]
Title: Multi-Antenna Relaying and Reconfigurable Intelligent Surfaces: End-to-End SNR and Achievable Rate
Subjects: Signal Processing (eess.SP); Information Theory (cs.IT)

In this report, we summarize the end-to-end signal-to-noise ratio and the rate of half-duplex, full-duplex, amplify-and-forward, and decode-and-forward relay-aided communications, and well as the signal-to-noise ratio and the rate of the emerging technology known as reconfigurable intelligent surfaces.

[182]  arXiv:1908.07980 (cross-list from math.OC) [pdf, other]
Title: A tree-based radial basis function method for noisy parallel surrogate optimization
Subjects: Optimization and Control (math.OC); Machine Learning (cs.LG); Machine Learning (stat.ML)

Parallel surrogate optimization algorithms have proven to be efficient methods for solving expensive noisy optimization problems. In this work we develop a new parallel surrogate optimization algorithm (ProSRS), using a novel tree-based "zoom strategy" to improve the efficiency of the algorithm. We prove that if ProSRS is run for sufficiently long, with probability converging to one there will be at least one point among all the evaluations that will be arbitrarily close to the global minimum. We compare our algorithm to several state-of-the-art Bayesian optimization algorithms on a suite of standard benchmark functions and two real machine learning hyperparameter-tuning problems. We find that our algorithm not only achieves significantly faster optimization convergence, but is also 1-4 orders of magnitude cheaper in computational cost.

[183]  arXiv:1908.07996 (cross-list from math.DS) [pdf, other]
Title: Time Delay in the Swing Equation: A Variety of Bifurcations
Comments: 12 pages, 6 figures, "The following article has been submitted to 'Chaos: An Interdisciplinary Journal of Nonlinear Science'. After it is published, it will be found at this https URL"
Subjects: Dynamical Systems (math.DS); Systems and Control (eess.SY)

The present paper addresses the swing equation with additional delayed damping as an example for pendulum-like systems. In this context, it is proved that recurring sub- and supercritical Hopf bifurcations occur if time delay is increased. To this end, a general formula for the first Lyapunov coefficient in second order systems with additional delayed damping and delay-free nonlinearity is given. In so far the paper extends results about stability switching of equilibria in linear time delay systems from Cooke and Grossmann and complements an analysis of Campbell et al., who consider time delay in the restoring force. In addition to the analytical results, periodic solutions are numerically dealt with. The numerical results demonstrate how a variety of qualitative behaviors is generated in the simple swing equation by only introducing time delay in a damping term.
keywords: retarded functional differential equation (RFDE); delay differential equation (DDE); bifurcation analysis; Hopf bifurcation; first Lyapunov coefficient; limit cycle; period doubling cascade; invariant torus; driven pendulum equation; power system stability

[184]  arXiv:1908.07999 (cross-list from q-fin.ST) [pdf, other]
Title: HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction
Subjects: Statistical Finance (q-fin.ST); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE)

Many researchers both in academia and industry have long been interested in the stock market. Numerous approaches were developed to accurately predict future trends in stock prices. Recently, there has been a growing interest in utilizing graph-structured data in computer science research communities. Methods that use relational data for stock market prediction have been recently proposed, but they are still in their infancy. First, the quality of collected information from different types of relations can vary considerably. No existing work has focused on the effect of using different types of relations on stock market prediction or finding an effective way to selectively aggregate information on different relation types. Furthermore, existing works have focused on only individual stock prediction which is similar to the node classification task. To address this, we propose a hierarchical attention network for stock prediction (HATS) which uses relational data for stock market prediction. Our HATS method selectively aggregates information on different relation types and adds the information to the representations of each company. Specifically, node representations are initialized with features extracted from a feature extraction module. HATS is used as a relational modeling module with initialized node representations. Then, node representations with the added information are fed into a task-specific layer. Our method is used for predicting not only individual stock prices but also market index movements, which is similar to the graph classification task. The experimental results show that performance can change depending on the relational data used. HATS which can automatically select information outperformed all the existing methods.

[185]  arXiv:1908.08004 (cross-list from eess.IV) [pdf, other]
Title: Pixel-wise Segmentation of Right Ventricle of Heart
Comments: Accepted at IEEE TENCON 2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)

One of the first steps in the diagnosis of most cardiac diseases, such as pulmonary hypertension, coronary heart disease is the segmentation of ventricles from cardiac magnetic resonance (MRI) images. Manual segmentation of the right ventricle requires diligence and time, while its automated segmentation is challenging due to shape variations and illdefined borders. We propose a deep learning based method for the accurate segmentation of right ventricle, which does not require post-processing and yet it achieves the state-of-the-art performance of 0.86 Dice coefficient and 6.73 mm Hausdorff distance on RVSC-MICCAI 2012 dataset. We use a novel adaptive cost function to counter extreme class-imbalance in the dataset. We present a comprehensive comparative study of loss functions, architectures, and ensembling techniques to build a principled approach for biomedical segmentation tasks.

[186]  arXiv:1908.08024 (cross-list from q-bio.NC) [pdf, other]
Title: Mapping of Local and Global Synapses on Spiking Neuromorphic Hardware
Comments: 17 pages, 7 figures, published in 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Subjects: Neurons and Cognition (q-bio.NC); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)

Spiking Neural Networks (SNNs) are widely deployed to solve complex pattern recognition, function approximation and image classification tasks. With the growing size and complexity of these networks, hardware implementation becomes challenging because scaling up the size of a single array (crossbar) of fully connected neurons is no longer feasible due to strict energy budget. Modern neromorphic hardware integrates small-sized crossbars with time-multiplexed interconnects. Partitioning SNNs becomes essential in order to map them on neuromorphic hardware with the major aim to reduce the global communication latency and energy overhead. To achieve this goal, we propose our instantiation of particle swarm optimization, which partitions SNNs into local synapses (mapped on crossbars) and global synapses (mapped on time-multiplexed interconnects), with the objective of reducing spike communication on the interconnect. This improves latency, power consumption as well as application performance by reducing inter-spike interval distortion and spike disorders. Our framework is implemented in Python, interfacing CARLsim, a GPU-accelerated application-level spiking neural network simulator with an extended version of Noxim, for simulating time-multiplexed interconnects. Experiments are conducted with realistic and synthetic SNN-based applications with different computation models, topologies and spike coding schemes. Using power numbers from in-house neuromorphic chips, we demonstrate significant reductions in energy consumption and spike latency over PACMAN, the widely-used partitioning technique for SNNs on SpiNNaker.

### Replacements for Thu, 22 Aug 19

[187]  arXiv:1607.02330 (replaced) [pdf, other]
Title: Two Measures of Dependence
Comments: 40 pages; 1 figure; published in Entropy
Journal-ref: Entropy 2019, 21(8), 778
Subjects: Information Theory (cs.IT)
[188]  arXiv:1609.08326 (replaced) [pdf, other]
Title: Asynchronous Stochastic Gradient Descent with Delay Compensation
Journal-ref: International Conference on Machine Learning. 2017: 4120-4129
Subjects: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
[189]  arXiv:1701.07179 (replaced) [pdf, other]
Title: Malicious URL Detection using Machine Learning: A Survey
Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
[190]  arXiv:1707.03324 (replaced) [pdf, ps, other]
Title: Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization
Subjects: Optimization and Control (math.OC); Computational Complexity (cs.CC); Machine Learning (cs.LG); Machine Learning (stat.ML)
[191]  arXiv:1711.00104 (replaced) [pdf]
Title: A Multiple Data Source Framework for the Identification of Activities of Daily Living Based on Mobile Device Data
Subjects: Computers and Society (cs.CY); Data Analysis, Statistics and Probability (physics.data-an)
[192]  arXiv:1712.06283 (replaced) [pdf, other]
Title: A Bridge Between Hyperparameter Optimization and Learning-to-learn
Comments: NIPS 2017 workshop on Meta-learning (this http URL)
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[193]  arXiv:1801.09250 (replaced) [pdf, other]
Title: Virtual Breakpoints for x86/64
Comments: 12 Pages, Presented at BSides Las Vegas 2019
Subjects: Operating Systems (cs.OS); Cryptography and Security (cs.CR)
[194]  arXiv:1804.03032 (replaced) [pdf, other]
Title: Approximate k-NN Graph Construction: a Generic Online Approach
Authors: Wan-Lei Zhao
Subjects: Information Retrieval (cs.IR); Computer Vision and Pattern Recognition (cs.CV)
[195]  arXiv:1804.10684 (replaced) [pdf, other]
Title: Joint Shape Representation and Classification for Detecting PDAC
Comments: Accepted to MICCAI 2019 Workshop(MLMI)(8 pages, 3 figures)
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[196]  arXiv:1805.04625 (replaced) [pdf, ps, other]
Title: Strong Converse using Change of Measure Arguments
Comments: 35 pages, no figure; v2 updated references
Subjects: Information Theory (cs.IT)
[197]  arXiv:1805.05208 (replaced) [pdf, other]
Title: Theoretically Efficient Parallel Graph Algorithms Can Be Fast and Scalable
Comments: This is the full version of the paper appearing in the ACM Symposium on Parallelism in Algorithms and Architectures (SPAA), 2018
Subjects: Data Structures and Algorithms (cs.DS); Distributed, Parallel, and Cluster Computing (cs.DC)
[198]  arXiv:1805.07451 (replaced) [pdf, ps, other]
Title: Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
Subjects: Numerical Analysis (math.NA); Machine Learning (cs.LG); Machine Learning (stat.ML)
[199]  arXiv:1805.10344 (replaced) [pdf, other]
Title: Pathology Segmentation using Distributional Differences to Images of Healthy Origin
Journal-ref: In International MICCAI Brainlesion Workshop, pp. 228-238. Springer, Cham, 2018
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[200]  arXiv:1806.00287 (replaced) [pdf]
Title: On Performance of Peer Review for Academic Journals: Analysis Based on Distributed Parallel System
Journal-ref: IEEE Access, 2019, 7, pp. 19024-19032
Subjects: Digital Libraries (cs.DL); Social and Information Networks (cs.SI)
[201]  arXiv:1806.02075 (replaced) [pdf, ps, other]
Title: Diffix-Birch: Extending Diffix-Aspen
Subjects: Cryptography and Security (cs.CR); Databases (cs.DB)
[202]  arXiv:1807.01359 (replaced) [pdf, other]
Title: Revisiting the Jones eigenproblem in fluid-structure interaction
Subjects: Numerical Analysis (math.NA)
[203]  arXiv:1807.06918 (replaced) [pdf]
Title: RARD II: The 94 Million Related-Article Recommendation Dataset
Journal-ref: 1st Workshop on Algorithm Selection and Meta-Learning in Information Retrieval (AMIR). 2019
Subjects: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL); Machine Learning (cs.LG)
[204]  arXiv:1807.09741 (replaced) [pdf, other]
Title: PADME: A Deep Learning-based Framework for Drug-Target Interaction Prediction
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[205]  arXiv:1807.10884 (replaced) [pdf, other]
Title: Physical Unclonable Function-based Key Sharing for IoT Security
Journal-ref: IEEE Transactions on Industrial Electronics (2019)
Subjects: Cryptography and Security (cs.CR)
[206]  arXiv:1808.10593 (replaced) [pdf, other]
Title: Asymptotic Seed Bias in Respondent-driven Sampling
Subjects: Statistics Theory (math.ST); Social and Information Networks (cs.SI); Probability (math.PR); Methodology (stat.ME)
[207]  arXiv:1809.04618 (replaced) [pdf, other]
Title: Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration
Subjects: Optimization and Control (math.OC); Machine Learning (cs.LG)
[208]  arXiv:1809.09330 (replaced) [pdf, other]
Title: Improved Parallel Cache-Oblivious Algorithms for Dynamic Programming and Linear Algebra
Subjects: Data Structures and Algorithms (cs.DS)
[209]  arXiv:1811.00265 (replaced) [pdf, other]
Comments: Published at the journal Information Processing & Management
Journal-ref: Information Processing & Management, Volume 56, Issue 6, November 2019, 102098
Subjects: Artificial Intelligence (cs.AI)
[210]  arXiv:1811.08718 (replaced) [pdf, other]
Title: Close spatial arrangement of mutants favors and disfavors fixation
Authors: Yunming Xiao, Bin Wu
Subjects: Populations and Evolution (q-bio.PE); Computational Engineering, Finance, and Science (cs.CE)
[211]  arXiv:1811.10401 (replaced) [pdf, other]
Title: Kleene Algebra with Observations
Subjects: Logic in Computer Science (cs.LO); Formal Languages and Automata Theory (cs.FL)
[212]  arXiv:1811.10636 (replaced) [pdf, other]
Title: Evolving Space-Time Neural Architectures for Videos
Journal-ref: ICCV 2019
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
[213]  arXiv:1811.10983 (replaced) [pdf, other]
Title: GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[214]  arXiv:1812.02552 (replaced) [pdf, other]
Title: Learning to Predict Image-based Rendering Artifacts with Respect to a Hidden Reference Image
Subjects: Graphics (cs.GR)
[215]  arXiv:1812.03989 (replaced) [pdf, other]
Title: PIMBALL: Binary Neural Networks in Spintronic Memory
Subjects: Emerging Technologies (cs.ET)
[216]  arXiv:1812.04706 (replaced) [pdf, other]
Title: Rotation Invariant Descriptors for Galaxy Morphological Classification
Authors: Hubert Cecotti
Subjects: Computer Vision and Pattern Recognition (cs.CV); Astrophysics of Galaxies (astro-ph.GA)
[217]  arXiv:1812.07716 (replaced) [pdf]
Title: Prognosticating Autism Spectrum Disorder Using Artificial Neural Network: Levenberg-Marquardt Algorithm
Journal-ref: Archives of Clinical and Biomedical Research 2018, 2(6):188-197
Subjects: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM); Machine Learning (stat.ML)
[218]  arXiv:1812.09681 (replaced) [pdf, other]
Title: Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering
Subjects: Multimedia (cs.MM); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[219]  arXiv:1812.10384 (replaced) [pdf]
Title: Identification of Cancer -- Mesothelioma Disease Using Logistic Regression and Association Rule
Journal-ref: American Journal of Engineering and Applied Sciences 2018, 11(4):1310.1319
Subjects: Computers and Society (cs.CY); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM); Machine Learning (stat.ML)
[220]  arXiv:1812.10486 (replaced) [pdf]
Title: Forecasting Cardiology Admissions from Catheterization Laboratory
Comments: In: Proceedings of the 2019 IISE Annual Conference. Edited by Romeijn. HE, Schaefer. A, Thomas. R. Orlando: IISE; 2019
Subjects: Computers and Society (cs.CY); Machine Learning (stat.ML)
[221]  arXiv:1812.10735 (replaced) [pdf, other]
Title: CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis
Subjects: Computation and Language (cs.CL)
[222]  arXiv:1812.11028 (replaced) [pdf]
Title: Evaluating Patient Readmission Risk: A Predictive Analytics Approach
Journal-ref: American Journal of Engineering and Applied Sciences 2018, 11(4):1320.1331
Subjects: Computers and Society (cs.CY); Machine Learning (cs.LG); Machine Learning (stat.ML)
[223]  arXiv:1901.00756 (replaced) [pdf]
Title: Classification of Functioning, Disability, and Health for Children and Youth: ICF-CY Self Care (SCADI Dataset) Using Predictive Analytics
Comments: In: Proceedings of the 2019 IISE Annual Conference. Edited by Romeijn. HE, Schaefer. A, Thomas. R. Orlando: IISE; 2019
Subjects: Computers and Society (cs.CY); Machine Learning (cs.LG); Machine Learning (stat.ML)
[224]  arXiv:1902.00424 (replaced) [pdf, other]
Title: A low-rank projector-splitting integrator for the Vlasov--Maxwell equations with divergence correction
Subjects: Numerical Analysis (math.NA)
[225]  arXiv:1902.03634 (replaced) [pdf, other]
Title: Shallow Triple Stream Three-dimensional CNN (STSTNet) for Micro-expression Recognition
Comments: 5 pages, 1 figure, Accepted and published in IEEE FG 2019
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[226]  arXiv:1903.00597 (replaced) [pdf, ps, other]
Title: Block-Coordinate Minimization for Large SDPs with Block-Diagonal Constraints
Subjects: Optimization and Control (math.OC); Machine Learning (cs.LG)
[227]  arXiv:1903.09376 (replaced) [pdf, other]
Title: Deep Fictitious Play for Stochastic Differential Games
Authors: Ruimeng Hu
Subjects: Optimization and Control (math.OC); Computer Science and Game Theory (cs.GT); Machine Learning (stat.ML)
[228]  arXiv:1903.10645 (replaced) [pdf, other]
Title: An Alarm System For Segmentation Algorithm Based On Shape Model
Comments: Accepted to ICCV 2019 (10 pages, 4 figures)
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[229]  arXiv:1904.00378 (replaced) [pdf, other]
Title: MAT-Fly: an educational platform for simulating Unmanned Aerial Vehicles aimed to detect and track moving objects
Authors: Giuseppe Silano
Subjects: Robotics (cs.RO); Systems and Control (eess.SY)
[230]  arXiv:1904.01324 (replaced) [pdf, other]
Title: Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
Comments: In Proceedings of the 2019 IEEE International Conference on Computer Vision (ICCV)
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[231]  arXiv:1904.01431 (replaced) [pdf, ps, other]
Title: Fundamentals of computability logic
Authors: Giorgi Japaridze
Comments: arXiv admin note: substantial text overlap with arXiv:1612.04513; text overlap with arXiv:1107.3706, arXiv:1107.2284 by other authors
Subjects: Logic in Computer Science (cs.LO)
[232]  arXiv:1904.02013 (replaced) [pdf, ps, other]
Title: On the classical complexity of sampling from quantum interference of indistinguishable bosons
Comments: 12 pages, one figure; in Revision 3: formal proof of sampling complexity is given in new section 4 with new theorem 2. New section 5 discusses open problems
Subjects: Quantum Physics (quant-ph); Data Structures and Algorithms (cs.DS)
[233]  arXiv:1904.02034 (replaced) [pdf, other]
Title: Internal versus external balancing in the evaluation of graph-based number types
Subjects: Computational Geometry (cs.CG); Data Structures and Algorithms (cs.DS); Numerical Analysis (math.NA)
[234]  arXiv:1904.06346 (replaced) [pdf, other]
Title: Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[235]  arXiv:1904.06690 (replaced) [pdf, other]
Title: BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
Comments: To appear in CIKM 2019
Subjects: Information Retrieval (cs.IR); Machine Learning (cs.LG)
[236]  arXiv:1904.07750 (replaced) [pdf, other]
Title: Co-Separating Sounds of Visual Objects
Comments: ICCV 2019, Project page: this http URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[237]  arXiv:1904.08398 (replaced) [pdf, other]
Title: Improved Baselines for Document Classification Using BERT
Subjects: Computation and Language (cs.CL)
[238]  arXiv:1904.11152 (replaced) [pdf, other]
Title: Sequential Decision Fusion for Environmental Classification in Assistive Walking
Subjects: Robotics (cs.RO)
[239]  arXiv:1904.12825 (replaced) [pdf, ps, other]
Title: Using Uncertainty Data in Chance-Constrained Trajectory Planning
Journal-ref: 2019 18th European Control Conference (ECC)
Subjects: Systems and Control (eess.SY); Optimization and Control (math.OC)
[240]  arXiv:1905.00604 (replaced) [pdf, other]
Title: IRS-Enhanced OFDM: Power Allocation and Passive Array Optimization
Comments: to appear in IEEE GLOBECOM 2019. arXiv admin note: substantial text overlap with arXiv:1906.09956
Subjects: Signal Processing (eess.SP); Information Theory (cs.IT)
[241]  arXiv:1905.00931 (replaced) [pdf]
Title: Deep Learning in Alzheimer's disease: Diagnostic Classification and Prognostic Prediction using Neuroimaging Data
Journal-ref: Frontiers in Aging Neuroscience 11 (2019): 220
Subjects: Image and Video Processing (eess.IV); Machine Learning (cs.LG); Machine Learning (stat.ML)
[242]  arXiv:1905.01282 (replaced) [pdf, other]
Title: Learning Some Popular Gaussian Graphical Models without Condition Number Bounds
Comments: V2: Updated version with some new results
Subjects: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Statistics Theory (math.ST); Machine Learning (stat.ML)
[243]  arXiv:1905.07082 (replaced) [pdf, other]
Title: The Audio Auditor: Participant-Level Membership Inference in Internet of Things Voice Services
Comments: Accepted by PPML workshop. 4-pages except figures, references, and appendix
Subjects: Cryptography and Security (cs.CR); Sound (cs.SD); Audio and Speech Processing (eess.AS)
[244]  arXiv:1905.08903 (replaced) [pdf, other]
Title: Topology optimization on two-dimensional manifolds
Subjects: Computational Physics (physics.comp-ph); Computational Engineering, Finance, and Science (cs.CE); Optimization and Control (math.OC)
[245]  arXiv:1905.09423 (replaced) [pdf, ps, other]
Title: Set Constraints, Pattern Match Analysis, and SMT
Authors: Joseph Eremondi
Subjects: Programming Languages (cs.PL)
[246]  arXiv:1905.09888 (replaced) [pdf]
Title: Prognostic Value of Transfer Learning Based Features in Resectable Pancreatic Ductal Adenocarcinoma
Subjects: Quantitative Methods (q-bio.QM); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
[247]  arXiv:1905.10998 (replaced) [pdf, other]
Title: Modelling Early User-Game Interactions for Joint Estimation of Survival Time and Churn Probability
Comments: Submitted to IEEE Conference on Games 2019
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[248]  arXiv:1905.11672 (replaced) [pdf, other]
Title: Invertible generative models for inverse problems: mitigating representation error and dataset bias
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[249]  arXiv:1905.12563 (replaced) [pdf, other]
Title: Application of Different Simulated Spectral Data and Machine Learning to Estimate the Chlorophyll a Concentration of Several Inland Waters
Comments: This contribution was accepted for the IEEE Whispers 2019 in Amsterdam
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
[250]  arXiv:1905.12567 (replaced) [pdf, other]
Title: MQLV: Optimal Policy of Money Management in Retail Banking with Q-Learning
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[251]  arXiv:1906.00744 (replaced) [pdf, other]
Title: Hierarchical Decision Making by Generating and Following Natural Language Instructions
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
[252]  arXiv:1906.02825 (replaced) [pdf, other]
Title: XRAI: Better Attributions Through Regions
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
[253]  arXiv:1906.03815 (replaced) [pdf, other]
Title: Learning to Segment Skin Lesions from Noisy Annotations
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[254]  arXiv:1906.04264 (replaced) [pdf, other]
Title: Optimal In-field Routing for Full and Partial Field Coverage with Arbitrary Non-Convex Fields and Multiple Obstacle Areas
Comments: 12 pages, 2 columns, 7 figures, 3 tables
Subjects: Systems and Control (eess.SY)
[255]  arXiv:1906.04448 (replaced) [pdf, other]
Title: Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding
Subjects: Information Theory (cs.IT); Machine Learning (cs.LG)
[256]  arXiv:1906.05063 (replaced) [pdf, other]
Title: Multi-spatial Scale Event Detection from Geo-tagged Tweet Streams via Power-law Verification
Subjects: Social and Information Networks (cs.SI)
[257]  arXiv:1906.06469 (replaced) [pdf, ps, other]
Title: Approximate Normalization for Gradual Dependent Types
Journal-ref: Proc. ACM Program. Lang. 3, ICFP, Article 88 (July 2019), 30 pages
Subjects: Programming Languages (cs.PL)
[258]  arXiv:1906.09503 (replaced) [pdf, ps, other]
Title: LNL-FPC: The Linear/Non-linear Fixpoint Calculus
Comments: Extended version of the ICFP paper "Mixed linear and non-linear recursive types" available at this https URL
Subjects: Programming Languages (cs.PL); Logic in Computer Science (cs.LO); Category Theory (math.CT)
[259]  arXiv:1906.09884 (replaced) [pdf, ps, other]
Title: Cross-Channel Correlation Preserved Three-Stream Lightweight CNNs for Demosaicking
Comments: This paper, originally titled as "Color Dedemosaicking by Parallel CNNs Leveraging Cross-Channel Difference", was submitted to conference IJCAI 2019 for peer review at Feb. 14 2019 via the conference submission system. The submission was rejected. The August arxiv version of this paper is as same as its June arxiv version. We add these comments only
Subjects: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM); Image and Video Processing (eess.IV)
[260]  arXiv:1907.00102 (replaced) [pdf, ps, other]
Title: The Complexity of Tiling Problems
Subjects: Computational Complexity (cs.CC)
[261]  arXiv:1907.02731 (replaced) [pdf, other]
Title: A Spectral Approach to Unsupervised Object Segmentation in Video
Comments: 8+1 pages, 9 figures, 3 tables, in review
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[262]  arXiv:1907.03191 (replaced) [pdf, other]
Title: TEAGS: Time-aware Text Embedding Approach to Generate Subgraphs
Subjects: Information Retrieval (cs.IR); Databases (cs.DB); Machine Learning (cs.LG)
[263]  arXiv:1907.03965 (replaced) [pdf, other]
Title: Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[264]  arXiv:1907.06357 (replaced) [pdf, other]
Title: Entanglement-assisted Quantum Codes from Algebraic Geometry Codes
Comments: Some results in this paper were presented at the 2019 IEEE International Symposium on Information Theory
Subjects: Information Theory (cs.IT); Quantum Physics (quant-ph)
[265]  arXiv:1907.08704 (replaced) [pdf, ps, other]
Title: Stronger and Faster Side-Channel Protections for CSIDH
Comments: This work has been accepted in LATINCRYPT-2019
Subjects: Cryptography and Security (cs.CR)
[266]  arXiv:1907.09350 (replaced) [src]
Title: Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation
Comments: There is a problem in the Theorem 1. We will try to fix it and update a new version
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[267]  arXiv:1907.12915 (replaced) [pdf, other]
Title: Reg R-CNN: Lesion Detection and Grading under Noisy Labels
Comments: 9 pages, 3 figures, 1 table
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[268]  arXiv:1908.00301 (replaced) [pdf, other]
Title: General Information Theory: Time and Information
Authors: Yilun Liu, Lidong Zhu
Comments: This work has been submitted to the IEEE T-IT for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
Subjects: Information Theory (cs.IT)
[269]  arXiv:1908.01703 (replaced) [pdf, other]
Title: SESF-Fuse: An Unsupervised Deep Model for Multi-Focus Image Fusion
Comments: technological report and fix some errors
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[270]  arXiv:1908.03451 (replaced) [pdf, other]
Title: Interactive Variance Attention based Online Spoiler Detection for Time-Sync Comments
Subjects: Information Retrieval (cs.IR); Computation and Language (cs.CL); Multimedia (cs.MM)
[271]  arXiv:1908.03480 (replaced) [pdf, other]
Title: Artificially Evolved Chunks for Morphosyntactic Analysis
Comments: To be published in proceedings of the 18th International Workshop on Treebanks and Linguistic Theories
Subjects: Computation and Language (cs.CL)
[272]  arXiv:1908.04030 (replaced) [pdf, other]
Title: Modeling continuous-time stochastic processes using $\mathcal{N}$-Curve mixtures
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[273]  arXiv:1908.04101 (replaced) [pdf]
Title: Microservices Anti Patterns: A Taxonomy
Comments: Microservices - Science and Engineering Springer 2019
Subjects: Software Engineering (cs.SE)
[274]  arXiv:1908.04209 (replaced) [pdf, other]
Title: Mixture-based Multiple Imputation Model for Clinical Data with a Temporal Dimension
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[275]  arXiv:1908.04364 (replaced) [pdf, other]
Comments: 8 pages, 7 figures; IJCAI-19; first three authors contribute equally. Data and code available at this https URL
Subjects: Computation and Language (cs.CL); Information Retrieval (cs.IR)
[276]  arXiv:1908.04683 (replaced) [pdf, other]
Title: Is Deep Reinforcement Learning Really Superhuman on Atari?
Subjects: Artificial Intelligence (cs.AI)
[277]  arXiv:1908.05287 (replaced) [pdf]
Title: Optimizing Ensemble Weights and Hyperparameters of Machine Learning Models for Regression Problems
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
[278]  arXiv:1908.05361 (replaced) [pdf, ps, other]
Title: Placing quantified variants of 3-SAT and Not-All-Equal 3-SAT in the polynomial hierarchy
Comments: 36 pages; reference corrected in introduction (the result of Karpinski and Piecuch establishes NP-completeness of Not-All-Equal 3-SAT if each variable appears *at most* four times)
Subjects: Computational Complexity (cs.CC)
[279]  arXiv:1908.05640 (replaced) [pdf, other]
Title: A Bayesian Choice Model for Eliminating Feedback Loops
Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)
[280]  arXiv:1908.05743 (replaced) [pdf, other]
Title: State-of-the-art Speech Recognition using EEG and Towards Decoding of Speech Spectrum From EEG
Comments: Extended version of paper which is under review. arXiv admin note: text overlap with arXiv:1906.08871
Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)
[281]  arXiv:1908.05968 (replaced) [pdf, other]
Title: N2D:(Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[282]  arXiv:1908.06315 (replaced) [pdf, other]
Title: Implicit Deep Learning
Subjects: Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML)
[283]  arXiv:1908.06319 (replaced) [pdf, other]
Title: Locally Linear Embedding and fMRI feature selection in psychiatric classification
Authors: Gagan Sidhu
Comments: Main article is 10 pages. Supplementary Information is approximately 20 pages and includes figures/results for six additional datasets, along with performance plots (as a function of dimensionality parameter 'd'), proportion(s) of brain regions defined by the respective atlases, subject ID partitioning for all eleven datasets
Journal-ref: IEEE Journal of Translational Engineering in Health & Medicine 7:10, 2019
Subjects: Image and Video Processing (eess.IV); Machine Learning (cs.LG); Machine Learning (stat.ML)
[284]  arXiv:1908.06417 (replaced) [pdf, other]
Title: On a progressive and iterative approximation method with memory for least square fitting
Subjects: Numerical Analysis (math.NA)
[285]  arXiv:1908.06520 (replaced) [pdf, other]
Title: Modeling Islamist Extremist Communications on Social Media using Contextual Dimensions: Religion, Ideology, and Hate
Subjects: Social and Information Networks (cs.SI); Computation and Language (cs.CL)
[286]  arXiv:1908.06543 (replaced) [pdf, other]
Title: Benchmarks for Graph Embedding Evaluation
Subjects: Social and Information Networks (cs.SI); Machine Learning (cs.LG)
[287]  arXiv:1908.06601 (replaced) [pdf]
Title: Implicit Recursive Characteristics of STOP
Authors: Mike H. Ji
Comments: 5 pages. A proof that STOP itself is a recursive process. STOP$_{\alpha X} = \mu$ X. nil $\rightarrow$ X
Subjects: Programming Languages (cs.PL); Computation and Language (cs.CL); Formal Languages and Automata Theory (cs.FL); Logic in Computer Science (cs.LO)
[288]  arXiv:1908.06647 (replaced) [pdf, other]
Title: RANet: Ranking Attention Network for Fast Video Object Segmentation
Comments: Accepted by ICCV 2019. 10 pages, 7 figures, 6 tables. The supplementary file can be found at this https URL Code is available at this https URL
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[289]  arXiv:1908.06746 (replaced) [pdf]
Title: Maize Yield and Nitrate Loss Prediction with Machine Learning Algorithms
Subjects: Other Quantitative Biology (q-bio.OT); Machine Learning (cs.LG); Applications (stat.AP); Machine Learning (stat.ML)
[290]  arXiv:1908.06891 (replaced) [pdf, ps, other]
Title: Weil descent and cryptographic trilinear maps
Subjects: Cryptography and Security (cs.CR); Number Theory (math.NT)
[291]  arXiv:1908.06954 (replaced) [pdf, other]
Title: Attention on Attention for Image Captioning
Comments: Accepted to ICCV 2019 (Oral)
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[292]  arXiv:1908.07087 (replaced) [pdf, other]
Title: SliceNDice: Mining Suspicious Multi-attribute Entity Groups with Multi-view Graphs
Comments: Published in Proceedings of 2019 IEEE 6th International Conference on Data Science and Advanced Analytics (DSAA)
Subjects: Social and Information Networks (cs.SI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
[293]  arXiv:1908.07209 (replaced) [pdf, other]
Title: DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learning
Comments: Updates to this version 1. It is found that the model architecture described in Section 2.3 corresponds to an older version of our model. Updates are therefore made to this section to reflect the latest model architecture. Figure 5 is also updated accordingly. 2. Section 2.5 is added to improve the clarity of the manuscript. 3. Other minor updates to language and formatting
Subjects: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG)
[294]  arXiv:1908.07218 (replaced) [pdf, other]
Title: CA-EHN: Commonsense Word Analogy from E-HowNet
Subjects: Computation and Language (cs.CL)
[295]  arXiv:1908.07291 (replaced) [pdf, other]
Title: Computing Stable Demers Cartograms
Comments: Appears in the Proceedings of the 27th International Symposium on Graph Drawing and Network Visualization (GD 2019)
Subjects: Computational Geometry (cs.CG); Data Structures and Algorithms (cs.DS)
[296]  arXiv:1908.07344 (replaced) [pdf, other]
Title: Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation
Comments: Accepted at STACOM 2019 held in conjunction with MICCAI 2019
Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
[297]  arXiv:1908.07380 (replaced) [pdf, other]
Title: PAC-Bayes with Backprop
Subjects: Machine Learning (cs.LG); Machine Learning (stat.ML)
[298]  arXiv:1908.07498 (replaced) [pdf, other]
Title: Hotel Recommendation System