We gratefully acknowledge support from
the Simons Foundation
and member institutions

Computer Science

New submissions

[ total of 229 entries: 1-229 ]
[ showing up to 2000 entries per page: fewer | more ]

New submissions for Fri, 17 Nov 17

[1]  arXiv:1711.05734 [pdf, other]
Title: Chipmunk: A Systolically Scalable 0.9 mm${}^2$, 3.08 Gop/s/mW @ 1.2 mW Accelerator for Near-Sensor Recurrent Neural Network Inference
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Sound (cs.SD)

Recurrent neural networks (RNNs) are state-of-the-art in voice awareness/understanding and speech recognition. On-device computation of RNNs on low-power mobile and wearable devices would be key to applications such as zero-latency voice-based human-machine interfaces. Here we present Chipmunk, a small (<1 mm${}^2$) hardware accelerator for Long-Short Term Memory RNNs in UMC 65 nm technology capable to operate at a measured peak efficiency up to 3.08 Gop/s/mW at 1.24 mW peak power. To implement big RNN models without incurring in huge memory transfer overhead, multiple Chipmunk engines can cooperate to form a single systolic array. In this way, the Chipmunk architecture in a 75 tiles configuration can achieve real-time phoneme extraction on a demanding RNN topology proposed by Graves et al., consuming less than 13 mW of average power.

[2]  arXiv:1711.05738 [pdf, ps]
Title: The Neural Network Pushdown Automaton: Model, Stack and Learning Simulations
Subjects: Artificial Intelligence (cs.AI)

In order for neural networks to learn complex languages or grammars, they must have sufficient computational power or resources to recognize or generate such languages. Though many approaches have been discussed, one ob- vious approach to enhancing the processing power of a recurrent neural network is to couple it with an external stack memory - in effect creating a neural network pushdown automata (NNPDA). This paper discusses in detail this NNPDA - its construction, how it can be trained and how useful symbolic information can be extracted from the trained network.
In order to couple the external stack to the neural network, an optimization method is developed which uses an error function that connects the learning of the state automaton of the neural network to the learning of the operation of the external stack. To minimize the error function using gradient descent learning, an analog stack is designed such that the action and storage of information in the stack are continuous. One interpretation of a continuous stack is the probabilistic storage of and action on data. After training on sample strings of an unknown source grammar, a quantization procedure extracts from the analog stack and neural network a discrete pushdown automata (PDA). Simulations show that in learning deterministic context-free grammars - the balanced parenthesis language, 1*n0*n, and the deterministic Palindrome - the extracted PDA is correct in the sense that it can correctly recognize unseen strings of arbitrary length. In addition, the extracted PDAs can be shown to be identical or equivalent to the PDAs of the source grammars which were used to generate the training strings.

[3]  arXiv:1711.05747 [pdf, other]
Title: Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
Subjects: Sound (cs.SD); Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Audio and Speech Processing (eess.AS)

We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work demonstrates that GANs can effectively suppress additive noise in raw waveform speech signals, improving perceptual quality metrics; however this technique was not justified in the context of ASR. In this work, we conduct a detailed study to measure the effectiveness of GANs in enhancing speech contaminated by both additive and reverberant noise. Motivated by recent advances in image processing, we propose operating GANs on log-Mel filterbank spectra instead of waveforms, which requires less computation and is more robust to reverberant noise. While GAN enhancement improves the performance of a clean-trained ASR system on noisy speech, it falls short of the performance achieved by conventional multi-style training (MTR). By appending the GAN-enhanced features to the noisy inputs and retraining, we achieve a 7% WER improvement relative to the MTR system.

[4]  arXiv:1711.05764 [pdf, other]
Title: Online Allocation with Traffic Spikes: Mixing Adversarial and Stochastic Models
Subjects: Data Structures and Algorithms (cs.DS); Computer Science and Game Theory (cs.GT)

Motivated by Internet advertising applications, online allocation problems have been studied extensively in various adversarial and stochastic models. While the adversarial arrival models are too pessimistic, many of the stochastic (such as i.i.d or random-order) arrival models do not realistically capture uncertainty in predictions. A significant cause for such uncertainty is the presence of unpredictable traffic spikes, often due to breaking news or similar events. To address this issue, a simultaneous approximation framework has been proposed to develop algorithms that work well both in the adversarial and stochastic models; however, this framework does not enable algorithms that make good use of partially accurate forecasts when making online decisions. In this paper, we propose a robust online stochastic model that captures the nature of traffic spikes in online advertising. In our model, in addition to the stochastic input for which we have good forecasting, an unknown number of impressions arrive that are adversarially chosen. We design algorithms that combine a stochastic algorithm with an online algorithm that adaptively reacts to inaccurate predictions. We provide provable bounds for our new algorithms in this framework. We accompany our positive results with a set of hardness results showing that our algorithms are not far from optimal in this framework. As a byproduct of our results, we also present improved online algorithms for a slight variant of the simultaneous approximation framework.

[5]  arXiv:1711.05766 [pdf, other]
Title: Fast Predictive Simple Geodesic Regression
Comments: 19 pages, 10 figures, 13 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

Deformable image registration and regression are important tasks in medical image analysis. However, they are computationally expensive, especially when analyzing large-scale datasets that contain thousands of images. Hence, cluster computing is typically used, making the approaches dependent on such computational infrastructure. Even larger computational resources are required as study sizes increase. This limits the use of deformable image registration and regression for clinical applications and as component algorithms for other image analysis approaches. We therefore propose using a fast predictive approach to perform image registrations. In particular, we employ these fast registration predictions to approximate a simplified geodesic regression model to capture longitudinal brain changes. The resulting method is orders of magnitude faster than the standard optimization-based regression model and hence facilitates large-scale analysis on a single graphics processing unit (GPU). We evaluate our results on 3D brain magnetic resonance images (MRI) from the ADNI datasets.

[6]  arXiv:1711.05767 [pdf, other]
Title: Predicting vehicular travel times by modeling heterogeneous influences between arterial roads
Comments: 13 pages, conference
Subjects: Artificial Intelligence (cs.AI)

Predicting travel times of vehicles in urban settings is a useful and tangible quantity of interest in the context of intelligent transportation systems. We address the problem of travel time prediction in arterial roads using data sampled from probe vehicles. There is only a limited literature on methods using data input from probe vehicles. The spatio-temporal dependencies captured by existing data driven approaches are either too detailed or very simplistic. We strike a balance of the existing data driven approaches to account for varying degrees of influence a given road may experience from its neighbors, while controlling the number of parameters to be learnt. Specifically, we use a NoisyOR conditional probability distribution (CPD) in conjunction with a dynamic bayesian network (DBN) to model state transitions of various roads. We propose an efficient algorithm to learn model parameters. We propose an algorithm for predicting travel times on trips of arbitrary durations. Using synthetic and real world data traces we demonstrate the superior performance of the proposed method under different traffic conditions.

[7]  arXiv:1711.05769 [pdf, other]
Title: PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Subjects: Computer Vision and Pattern Recognition (cs.CV)

This paper presents a method for adding multiple tasks to a single deep neural network while avoiding catastrophic forgetting. Inspired by network pruning techniques, we exploit redundancies in large deep networks to free up parameters that can then be employed to learn new tasks. By performing iterative pruning and network re-training, we are able to sequentially "pack" multiple tasks into a single network while ensuring minimal drop in performance and minimal storage overhead. Unlike prior work that uses proxy losses to maintain accuracy on older tasks, we always optimize for the task at hand. We perform extensive experiments on a variety of network architectures and large-scale datasets, and observe much better robustness against catastrophic forgetting than prior work. In particular, we are able to add three fine-grained classification tasks to a single ImageNet-trained VGG-16 network and achieve accuracies close to those of separately trained networks for each task.

[8]  arXiv:1711.05772 [pdf, other]
Title: Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
Subjects: Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Machine Learning (stat.ML)

Deep generative neural networks have proven effective at both conditional and unconditional modeling of complex data distributions. Conditional generation enables interactive control, but creating new controls often requires expensive retraining. In this paper, we develop a method to condition generation without retraining the model. By post-hoc learning latent constraints, value functions that identify regions in latent space that generate outputs with desired attributes, we can conditionally sample from these regions with gradient-based optimization or amortized actor functions. Combining attribute constraints with a universal "realism" constraint, which enforces similarity to the data distribution, we generate realistic conditional images from an unconditional variational autoencoder. Further, using gradient-based optimization, we demonstrate identity-preserving transformations that make the minimal adjustment in latent space to modify the attributes of an image. Finally, with discrete sequences of musical notes, we demonstrate zero-shot conditional generation, learning latent constraints in the absence of labeled data or a differentiable reward function. Code with dedicated cloud instance has been made publicly available (https://goo.gl/STGMGx).

[9]  arXiv:1711.05775 [pdf]
Title: End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design
Authors: Li Shen
Comments: Accepted poster at NIPS 2017 Workshop on Machine Learning for Health (this https URL)
Subjects: Computer Vision and Pattern Recognition (cs.CV)

We develop an end-to-end training algorithm for whole-image breast cancer diagnosis based on mammograms. It requires lesion annotations only at the first stage of training. After that, a whole image classifier can be trained using only image level labels. This greatly reduced the reliance on lesion annotations. Our approach is implemented using an all convolutional design that is simple yet provides superior performance in comparison with the previous methods. On DDSM, our best single-model achieves a per-image AUC score of 0.88 and three-model averaging increases the score to 0.91. On INbreast, our best single-model achieves a per-image AUC score of 0.96. Using DDSM as benchmark, our models compare favorably with the current state-of-the-art. We also demonstrate that a whole image model trained on DDSM can be easily transferred to INbreast without using its lesion annotations and using only a small amount of training data. Code availability: https://github.com/lishen/end2end-all-conv

[10]  arXiv:1711.05780 [pdf, ps, other]
Title: Detecting Egregious Conversations between Customers and Virtual Agents
Subjects: Computation and Language (cs.CL)

Virtual agents are becoming a prominent channel of interaction in customer service. Not all customer interactions are smooth, however, and some can become almost comically bad. In such instances, a human agent might need to step in and salvage the conversation. Detecting bad conversations is important since disappointing customer service may threaten customer loyalty and impact revenue. In this paper, we outline an approach to detecting such egregious conversations, using behavioral cues from the user, patterns in agent responses, and user-agent interaction. Using logs of two commercial systems, we show that using these features improves the detection F1-score by around 20% over using textual features alone. In addition, we show that those features are common across two quite different domains and, arguably, universal.

[11]  arXiv:1711.05787 [pdf, other]
Title: WebRelate: Integrating Web Data with Spreadsheets using Examples
Comments: To appear in POPL 2018
Subjects: Databases (cs.DB); Programming Languages (cs.PL)

Data integration between web sources and relational data is a key challenge faced by data scientists and spreadsheet users. There are two main challenges in programmatically joining web data with relational data. First, most websites do not expose a direct interface to obtain tabular data, so the user needs to formulate a logic to get to different webpages for each input row in the relational table. Second, after reaching the desired webpage, the user needs to write complex scripts to extract the relevant data, which is often conditioned on the input data. Since many data scientists and end-users come from diverse backgrounds, writing such complex regular-expression based logical scripts to perform data integration tasks is unfortunately often beyond their programming expertise.
We present WebRelate, a system that allows users to join semi-structured web data with relational data in spreadsheets using input-output examples. WebRelate decomposes the web data integration task into two sub-tasks of i) URL learning and ii) input-dependent web extraction. The first sub-task generates the URLs for the webpages containing the desired data for all rows in the relational table. WebRelate achieves this by learning a string transformation program using a few example URLs. The second sub-task uses examples of desired data to be extracted from the corresponding webpages and learns a program to extract the data for the other rows. We design expressive domain-specific languages for URL generation and web data extraction, and present efficient synthesis algorithms for learning programs in these DSLs from few input-output examples. We evaluate WebRelate on 88 real-world web data integration tasks taken from online help forums and Excel product team, and show that WebRelate can learn the desired programs within few seconds using only 1 example for the majority of the tasks.

[12]  arXiv:1711.05788 [pdf, other]
Title: Quantile Markov Decision Process
Subjects: Artificial Intelligence (cs.AI)

In this paper, we consider the problem of optimizing the quantiles of the cumulative rewards of Markov Decision Processes (MDP), to which we refers as Quantile Markov Decision Processes (QMDP). Traditionally, the goal of a Markov Decision Process (MDP) is to maximize expected cumulative reward over a defined horizon (possibly to be infinite). In many applications, however, a decision maker may be interested in optimizing a specific quantile of the cumulative reward instead of its expectation. (If we have some reference here, it would be good.) Our framework of QMDP provides analytical results characterizing the optimal QMDP solution and presents the algorithm for solving the QMDP. We provide analytical results characterizing the optimal QMDP solution and present the algorithms for solving the QMDP. We illustrate the model with two experiments: a grid game and a HIV optimal treatment experiment.

[13]  arXiv:1711.05789 [pdf, other]
Title: CMU LiveMedQA at TREC 2017 LiveQA: A Consumer Health Question Answering System
Comments: To appear in Proceedings of TREC 2017
Subjects: Computation and Language (cs.CL); Information Retrieval (cs.IR)

In this paper, we present LiveMedQA, a question answering system that is optimized for consumer health question. On top of the general QA system pipeline, we introduce several new features that aim to exploit domain-specific knowledge and entity structures for better performance. This includes a question type/focus analyzer based on deep text classification model, a tree-based knowledge graph for answer generation and a complementary structure-aware searcher for answer retrieval. LiveMedQA system is evaluated in the TREC 2017 LiveQA medical subtask, where it received an average score of 0.356 on a 3 point scale. Evaluation results revealed 3 substantial drawbacks in current LiveMedQA system, based on which we provide a detailed discussion and propose a few solutions that constitute the main focus of our subsequent work.

[14]  arXiv:1711.05791 [pdf]
Title: Maintaining The Humanity of Our Models
Authors: Umang Bhatt
Comments: Under review for the 2018 AAAI Spring Symposium: AI and Society: Ethics, Safety and Trustworthiness in Intelligent Agents
Subjects: Computers and Society (cs.CY)

Artificial intelligence and machine learning has a major research interest in computer science for the better part of the last few decades. However, all too recently, both AI and ML have rapidly grown to be media frenzies, pressuring companies and researchers to claim they use these technologies. As ML continues to percolate into daily life, we, as computer scientists and machine learning researchers, are responsible for ensuring we clearly convey the extent of our work and the humanity of our models. Regularizing ML for mass adoption requires a rigorous standard for model interpretability, a deep consideration for human bias in data, and a transparent understanding of a model's societal effects.

[15]  arXiv:1711.05792 [pdf, other]
Title: A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration
Comments: Our manuscript is based on our conference paper with the same title published in 14th European Conference on Computer Vision (ECCV 2016, spotlight). It has been significantly extended and is now in journal submission
Subjects: Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)

We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time position follows a Gaussian mixture distribution, a fact exploited to softly match, aka register, the states in two HMMs. We refer to such HMMs as Gaussian mixture model-HMM (GMM-HMM). The registration of states is inspired by the intrinsic relationship of optimal transport and the Wasserstein metric between distributions. Specifically, the components of the marginal GMMs are matched by solving an optimal transport problem where the cost between components is the Wasserstein metric for Gaussian distributions. The solution of the optimization problem is a fast approximation to the Wasserstein metric between two GMMs. The new Aggregated Wasserstein distance is a semi-metric and can be computed without generating Monte Carlo samples. It is invariant to relabeling or permutation of states. The distance is defined meaningfully even for two HMMs that are estimated from data of different dimensionality, a situation that can arise due to missing variables. This distance quantifies the dissimilarity of GMM-HMMs by measuring both the difference between the two marginal GMMs and that between the two transition matrices. Our new distance is tested on tasks of retrieval, classification, and t-SNE visualization of time series. Experiments on both synthetic and real data have demonstrated its advantages in terms of accuracy as well as efficiency in comparison with existing distances based on the Kullback-Leibler divergence.

[16]  arXiv:1711.05795 [pdf, other]
Title: Finer Grained Entity Typing with TypeNet
Comments: Accepted at 6th Workshop on Automated Knowledge Base Construction (AKBC) at NIPS 2017
Subjects: Computation and Language (cs.CL); Neural and Evolutionary Computing (cs.NE)

We consider the challenging problem of entity typing over an extremely fine grained set of types, wherein a single mention or entity can have many simultaneous and often hierarchically-structured types. Despite the importance of the problem, there is a relative lack of resources in the form of fine-grained, deep type hierarchies aligned to existing knowledge bases. In response, we introduce TypeNet, a dataset of entity types consisting of over 1941 types organized in a hierarchy, obtained by manually annotating a mapping from 1081 Freebase types to WordNet. We also experiment with several models comparable to state-of-the-art systems and explore techniques to incorporate a structure loss on the hierarchy with the standard mention typing loss, as a first step towards future research on this dataset.

[17]  arXiv:1711.05799 [pdf, other]
Title: ORBIT: Ordering Based Information Transfer Across Space and Time for Global Surface Water Monitoring
Subjects: Learning (cs.LG); Geophysics (physics.geo-ph)

Many earth science applications require data at both high spatial and temporal resolution for effective monitoring of various ecosystem resources. Due to practical limitations in sensor design, there is often a trade-off in different resolutions of spatio-temporal datasets and hence a single sensor alone cannot provide the required information. Various data fusion methods have been proposed in the literature that mainly rely on individual timesteps when both datasets are available to learn a mapping between features values at different resolutions using local relationships between pixels. Earth observation data is often plagued with spatially and temporally correlated noise, outliers and missing data due to atmospheric disturbances which pose a challenge in learning the mapping from a local neighborhood at individual timesteps. In this paper, we aim to exploit time-independent global relationships between pixels for robust transfer of information across different scales. Specifically, we propose a new framework, ORBIT (Ordering Based Information Transfer) that uses relative ordering constraint among pixels to transfer information across both time and scales. The effectiveness of the framework is demonstrated for global surface water monitoring using both synthetic and real-world datasets.

[18]  arXiv:1711.05805 [pdf, other]
Title: Robust and Precise Vehicle Localization based on Multi-sensor Fusion in Diverse City Scenes
Comments: 8 pages, 6 figures, 2 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)

We present a robust and precise localization system that achieves centimeter-level localization accuracy in disparate city scenes. Our system adaptively uses information from complementary sensors such as GNSS, LiDAR, and IMU to achieve high localization accuracy and resilience in challenging scenes, such as urban downtown, highways, and tunnels. Rather than relying only on LiDAR intensity or 3D geometry, we make innovative use of LiDAR intensity and altitude cues to significantly improve localization system accuracy and robustness. Our GNSS RTK module utilizes the help of the multi-sensor fusion framework and achieves a better ambiguity resolution success rate. An error-state Kalman filter is applied to fuse the localization measurements from different sources with novel uncertainty estimation. We validate, in detail, the effectiveness of our approaches, achieving 5-10cm RMS accuracy and outperforming previous state-of-the-art systems. Importantly, our system, while deployed in a large autonomous driving fleet, made our vehicles fully autonomous in crowded city streets despite road construction that occurred from time to time. A dataset including more than 60 km real traffic driving in various urban roads is used to comprehensively test our system.

[19]  arXiv:1711.05809 [pdf, other]
Title: Hierarchical Modeling of Seed Variety Yields and Decision Making for Future Planting Plans
Subjects: Learning (cs.LG); Machine Learning (stat.ML)

Eradicating hunger and malnutrition is a key development goal of the 21st century. We address the problem of optimally identifying seed varieties to reliably increase crop yield within a risk-sensitive decision-making framework. Specifically, we introduce a novel hierarchical machine learning mechanism for predicting crop yield (the yield of different seed varieties of the same crop). We integrate this prediction mechanism with a weather forecasting model, and propose three different approaches for decision making under uncertainty to select seed varieties for planting so as to balance yield maximization and risk.We apply our model to the problem of soybean variety selection given in the 2016 Syngenta Crop Challenge. Our prediction model achieves a median absolute error of 3.74 bushels per acre and thus provides good estimates for input into the decision models.Our decision models identify the selection of soybean varieties that appropriately balance yield and risk as a function of the farmer's risk aversion level. More generally, our models support farmers in decision making about which seed varieties to plant.

[20]  arXiv:1711.05816 [pdf, ps, other]
Title: K3, L3, LP, RM3, A3, FDE: How to Make Many-Valued Logics Work for You
Subjects: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)

We investigate some well-known (and a few not-so-well-known) many-valued logics that have a small number (3 or 4) of truth values. For some of them we complain that they do not have any \emph{logical} use (despite their perhaps having some intuitive semantic interest) and we look at ways to add features so as to make them useful, while retaining their intuitive appeal. At the end, we show some surprising results in the system FDE, and its relationships with features of other logics. We close with some new examples of "synonymous logics." An Appendix contains a natural deduction system for our augmented FDE, and proofs of soundness and completeness.

[21]  arXiv:1711.05817 [pdf]
Title: Lagrange policy gradient
Comments: 6 pages, 4 figures
Subjects: Learning (cs.LG); Optimization and Control (math.OC)

Most algorithms for reinforcement learning work by estimating action-value functions. Here we present a method that uses Lagrange multipliers, the costate equation, and multilayer neural networks to compute policy gradients. We show that this method can find solutions to time-optimal control problems, driving nonlinear mechanical systems quickly to a target configuration. On these tasks its performance is comparable to that of deep deterministic policy gradient, a recent action-value method.

[22]  arXiv:1711.05818 [pdf, other]
Title: Fronthaul-Aware Group Sparse Precoding and Signal Splitting in SWIPT C-RAN
Comments: Accepted by IEEE Globecom 2017
Subjects: Information Theory (cs.IT)

We investigate the precoding, remote radio head (RRH) selection and signal splitting in the simultaneous wireless information and power transferring (SWIPT) cloud radio access networks \mbox{(C-RANs)}. The objective is to minimize the power consumption of the SWIPT C-RAN. Different from the existing literature, we consider the nonlinear fronthaul power consumption and the multiple antenna RRHs. By switching off the unnecessary RRHs, the group sparsity of the precoding coefficients is introduced, which indicates that the precoding process and the RRH selection are coupled. In order to overcome these issues, a group sparse precoding and signal splitting algorithm is proposed based on the majorization-minimization framework, and the convergence behavior is established. Numerical results are used to verify our proposed studies.

[23]  arXiv:1711.05820 [pdf, other]
Title: Zero-Shot Learning via Class-Conditioned Deep Generative Models
Comments: To appear in AAAI 2018
Subjects: Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen class using a class-specific latent-space distribution, conditioned on class attributes. We use these latent-space distributions as a prior for a supervised variational autoencoder (VAE), which also facilitates learning highly discriminative feature representations for the inputs. The entire framework is learned end-to-end using only the seen-class training data. The model infers corresponding attributes of a test image by maximizing the VAE lower bound; the inferred attributes may be linked to labels not seen when training. We further extend our model to a (1) semi-supervised/transductive setting by leveraging unlabeled unseen-class data via an unsupervised learning module, and (2) few-shot learning where we also have a small number of labeled inputs from the unseen classes. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of benchmark data sets.

[24]  arXiv:1711.05822 [pdf]
Title: Understanding the Changing Roles of Scientific Publications via Citation Embeddings
Comments: CLBib-2017: Second Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics
Subjects: Digital Libraries (cs.DL); Learning (cs.LG)

Researchers may describe different aspects of past scientific publications in their publications and the descriptions may keep changing in the evolution of science. The diverse and changing descriptions (i.e., citation context) on a publication characterize the impact and contributions of the past publication. In this article, we aim to provide an approach to understanding the changing and complex roles of a publication characterized by its citation context. We described a method to represent the publications' dynamic roles in science community in different periods as a sequence of vectors by training temporal embedding models. The temporal representations can be used to quantify how much the roles of publications changed and interpret how they changed. Our study in the biomedical domain shows that our metric on the changes of publications' roles is stable over time at the population level but significantly distinguish individuals. We also show the interpretability of our methods by a concrete example.

[25]  arXiv:1711.05824 [pdf]
Title: Security Issues in Controller Area Networks in Automobiles
Comments: 6 pages. 18th international conference on Sciences and Techniques of Automatic control & computer engineering - STA'2017, Monastir, Tunisia, December 21-23, 2017
Subjects: Cryptography and Security (cs.CR)

Modern vehicles may contain a considerable number of ECUs (Electronic Control Units) which are connected through various means of communication, with the CAN (Controller Area Network) protocol being the most widely used. However, several vulnerabilities such as the lack of authentication and the lack of data encryption have been pointed out by several authors, which eventually render vehicles unsafe to its users and surroundings. Moreover, the lack of security in modern automobiles has been studied and analyzed by other researchers as well as several reports about modern car hacking have been published. This work aimed to analyze and test the level of security in these systems, taking a BMW E90 (3-series) instrument cluster as a sample for a proof of concept study. A man in the middle attack was performed in order to send spoofed messages to the instrument cluster. This paper demonstrates a proof of concept study consisting of a rogue device built using cheap commercially available components while being connected to the same CAN-Bus in order to test the resilience of the CAN protocol.

[26]  arXiv:1711.05828 [pdf, other]
Title: BoostJet: Towards Combining Statistical Aggregates with Neural Embeddings for Recommendations
Comments: 9 pages, 9 figures
Subjects: Information Retrieval (cs.IR); Learning (cs.LG); Machine Learning (stat.ML)

Recommenders have become widely popular in recent years because of their broader applicability in many e-commerce applications. These applications rely on recommenders for generating advertisements for various offers or providing content recommendations. However, the quality of the generated recommendations depends on user features (like demography, temporality), offer features (like popularity, price), and user-offer features (like implicit or explicit feedback). Current state-of-the-art recommenders do not explore such diverse features concurrently while generating the recommendations.
In this paper, we first introduce the notion of Trackers which enables us to capture the above-mentioned features and thus incorporate users' online behaviour through statistical aggregates of different features (demography, temporality, popularity, price). We also show how to capture offer-to-offer relations, based on their consumption sequence, leveraging neural embeddings for offers in our Offer2Vec algorithm. We then introduce BoostJet, a novel recommender which integrates the Trackers along with the neural embeddings using MatrixNet, an efficient distributed implementation of gradient boosted decision tree, to improve the recommendation quality significantly. We provide an in-depth evaluation of BoostJet on Yandex's dataset, collecting online behaviour from tens of millions of online users, to demonstrate the practicality of BoostJet in terms of recommendation quality as well as scalability.

[27]  arXiv:1711.05839 [pdf, ps, other]
Title: Cograph Editing in $O(3^n n)$ time and $O(2^n)$ space
Comments: 7 pages
Subjects: Data Structures and Algorithms (cs.DS)

We present a dynamic programming algorithm for optimally solving the \textsc{Cograph Editing} problem on an $n$-vertex graph that runs in $O(3^n n)$ time and uses $O(2^n)$ space. In this problem, we are given a graph $G = (V, E)$ and the task is to find a smallest possible set $F \subseteq V \times V$ of vertex pairs such that $(V, E \bigtriangleup F)$ is a cograph (or $P_4$-free graph), where $\bigtriangleup$ represents the symmetric difference operator. We also describe a technique for speeding up the performance of the algorithm in practice.

[28]  arXiv:1711.05847 [pdf, other]
Title: AOGNets: Deep AND-OR Grammar Networks for Visual Recognition
Comments: 10 pages
Subjects: Computer Vision and Pattern Recognition (cs.CV)

This paper presents a method of learning deep AND-OR Grammar (AOG) networks for visual recognition, which we term AOGNets. An AOGNet consists of a number of stages each of which is composed of a number of AOG building blocks. An AOG building block is designed based on a principled AND-OR grammar and represented by a hierarchical and compositional AND-OR graph. Each node applies some basic operation (e.g., Conv-BatchNorm-ReLU) to its input. There are three types of nodes: an AND-node explores composition, whose input is computed by concatenating features of its child nodes; an OR-node represents alternative ways of composition in the spirit of exploitation, whose input is the element-wise sum of features of its child nodes; and a Terminal-node takes as input a channel-wise slice of the input feature map of the AOG building block. AOGNets aim to harness the best of two worlds (grammar models and deep neural networks) in representation learning with end-to-end training. In experiments, AOGNets are tested on three highly competitive image classification benchmarks: CIFAR-10, CIFAR-100 and ImageNet-1K. AOGNets obtain better performance than the widely used Residual Net and its variants, and are tightly comparable to the Dense Net. AOGNets are also tested in object detection on the PASCAL VOC 2007 and 2012 using the vanilla Faster RCNN system and obtain better performance than the Residual Net.

[29]  arXiv:1711.05848 [pdf, other]
Title: Knowledge transfer for surgical activity prediction
Subjects: Learning (cs.LG)

Lack of training data hinders automatic recognition and prediction of surgical activities necessary for situation-aware operating rooms. We propose using knowledge transfer to compensate for data deficit and improve prediction. We used two approaches to extract and transfer surgical process knowledge. First, we encoded semantic information about surgical terms using word embedding which boosted learning process. Secondly, we passed knowledge between different clinical datasets of neurosurgical procedures using transfer learning. Transfer learning was shown to be more effective than a simple combination of data, especially for less similar procedures. The combination of two methods provided 22% improvement of activity prediction. We also made several pertinent observations about surgical practices.

[30]  arXiv:1711.05851 [pdf, other]
Title: Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
Comments: ICLR 2018 submission
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new relations by combinatory reasoning over the information found along other paths connecting a pair of entities. Given the enormous size of KBs and the exponential number of paths, previous path-based models have considered only the problem of predicting a missing relation given two entities or evaluating the truth of a proposed triple. Additionally, these methods have traditionally used random paths between fixed entity pairs or more recently learned to pick paths between them. We propose a new algorithm MINERVA, which addresses the much more difficult and practical task of answering questions where the relation is known, but only one entity. Since random walks are impractical in a setting with combinatorially many destinations from a start node, we present a neural reinforcement learning approach which learns how to navigate the graph conditioned on the input query to find predictive paths. Empirically, this approach obtains state-of-the-art results on several datasets, significantly outperforming prior methods.

[31]  arXiv:1711.05852 [pdf, other]
Title: Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy
Subjects: Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Neural and Evolutionary Computing (cs.NE)

Deep learning networks have achieved state-of-the-art accuracies on computer vision workloads like image classification and object detection. The performant systems, however, typically involve big models with numerous parameters. Once trained, a challenging aspect for such top performing models is deployment on resource constrained inference systems - the models (often deep networks or wide networks or both) are compute and memory intensive. Low-precision numerics and model compression using knowledge distillation are popular techniques to lower both the compute requirements and memory footprint of these deployed models. In this paper, we study the combination of these two techniques and show that the performance of low-precision networks can be significantly improved by using knowledge distillation techniques. Our approach, Apprentice, achieves state-of-the-art accuracies using ternary precision and 4-bit precision for variants of ResNet architecture on ImageNet dataset. We present three schemes using which one can apply knowledge distillation techniques to various stages of the train-and-deploy pipeline.

[32]  arXiv:1711.05857 [pdf, other]
Title: An Optimal and Progressive Approach to Online Search of Top-k Important Communities
Subjects: Databases (cs.DB); Social and Information Networks (cs.SI)

Community search over large graphs is a fundamental problem in graph analysis. Recent studies also propose to compute top-k important communities, where each reported community not only is a cohesive subgraph but also has a high importance value. The existing approaches to the problem of importance-based top-k community search are either index- based algorithms or online search algorithms without indexes. As the index-based algorithms need to pre-compute a special- purpose index and can only work for one built-in vertex weight vector, in this paper we study the online search approach. Considering the limitation of the existing online search algorithms that need to traverse the entire graph, in this paper we propose an optimal online search algorithm LocalSearch whose time complexity is linearly proportional to the size of the smallest subgraph that a correct algorithm needs to access without index. Moreover, we propose techniques to make LocalSearch progressively compute and report the communities in decreasing importance order such that k does not need to be specified in the query. Finally, we also extend our techniques to the general case of importance-based top-k community search regard- ing other cohesiveness measures. Extensive empirical studies on real graphs demonstrate that our algorithms outperform the existing online search algorithms by several orders of magnitude.

[33]  arXiv:1711.05858 [pdf, other]
Title: End-to-end 3D shape inverse rendering of different classes of objects from a single input image
Comments: 16 pages, 12 figures, 2 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

In this paper a semi-supervised deep framework is proposed for the problem of 3D shape inverse rendering from a single 2D input image. The main structure of proposed framework consists of unsupervised pre-trained components which significantly reduce the need to labeled data for training the whole framework. using labeled data has the advantage of achieving to accurate results without the need to predefined assumptions about image formation process. Three main components are used in the proposed network: an encoder which maps 2D input image to a representation space, a 3D decoder which decodes a representation to a 3D structure and a mapping component in order to map 2D to 3D representation. The only part that needs label for training is the mapping part with not too many parameters. The other components in the network can be pre-trained unsupervised using only 2D images or 3D data in each case. The way of reconstructing 3D shapes in the decoder component, inspired by the model based methods for 3D reconstruction, maps a low dimensional representation to 3D shape space with the advantage of extracting the basis vectors of shape space from training data itself and is not restricted to a small set of examples as used in predefined models. Therefore, the proposed framework deals directly with coordinate values of the point cloud representation which leads to achieve dense 3D shapes in the output. The experimental results on several benchmark datasets of objects and human faces and comparing with recent similar methods shows the power of proposed network in recovering more details from single 2D images.

[34]  arXiv:1711.05859 [pdf, other]
Title: Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification
Comments: 8 pages
Subjects: Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG)

Network biology has been successfully used to help reveal complex mechanisms of disease, especially cancer. On the other hand, network biology requires in-depth knowledge to construct disease-specific networks, but our current knowledge is very limited even with the recent advances in human cancer biology. Deep learning has shown a great potential to address the difficult situation like this. However, deep learning technologies conventionally use grid-like structured data, thus application of deep learning technologies to the classification of human disease subtypes is yet to be explored. Recently, graph based deep learning techniques have emerged, which becomes an opportunity to leverage analyses in network biology. In this paper, we proposed a hybrid model, which integrates two key components 1) graph convolution neural network (graph CNN) and 2) relation network (RN). We utilize graph CNN as a component to learn expression patterns of cooperative gene community, and RN as a component to learn associations between learned patterns. The proposed model is applied to the PAM50 breast cancer subtype classification task, the standard breast cancer subtype classification of clinical utility. In experiments of both subtype classification and patient survival analysis, our proposed method achieved significantly better performances than existing methods. We believe that this work is an important starting point to realize the upcoming personalized medicine.

[35]  arXiv:1711.05860 [pdf]
Title: A General Neural Network Hardware Architecture on FPGA
Authors: Yufeng Hao
Subjects: Computer Vision and Pattern Recognition (cs.CV); Hardware Architecture (cs.AR); Neural and Evolutionary Computing (cs.NE)

Field Programmable Gate Arrays (FPGAs) plays an increasingly important role in data sampling and processing industries due to its highly parallel architecture, low power consumption, and flexibility in custom algorithms. Especially, in the artificial intelligence field, for training and implement the neural networks and machine learning algorithms, high energy efficiency hardware implement and massively parallel computing capacity are heavily demanded. Therefore, many global companies have applied FPGAs into AI and Machine learning fields such as autonomous driving and Automatic Spoken Language Recognition (Baidu) [1] [2] and Bing search (Microsoft) [3]. Considering the FPGAs great potential in these fields, we tend to implement a general neural network hardware architecture on XILINX ZU9CG System On Chip (SOC) platform [4], which contains abundant hardware resource and powerful processing capacity. The general neural network architecture on the FPGA SOC platform can perform forward and backward algorithms in deep neural networks (DNN) with high performance and easily be adjusted according to the type and scale of the neural networks.

[36]  arXiv:1711.05861 [pdf, ps, other]
Title: Modal Regression based Atomic Representation for Robust Face Recognition
Comments: 10 pages, 9 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Representation based classification (RC) methods such as sparse RC (SRC) have shown great potential in face recognition in recent years. Most previous RC methods are based on the conventional regression models, such as lasso regression, ridge regression or group lasso regression. These regression models essentially impose a predefined assumption on the distribution of the noise variable in the query sample, such as the Gaussian or Laplacian distribution. However, the complicated noises in practice may violate the assumptions and impede the performance of these RC methods. In this paper, we propose a modal regression based atomic representation and classification (MRARC) framework to alleviate such limitation. Unlike previous RC methods, the MRARC framework does not require the noise variable to follow any specific predefined distributions. This gives rise to the capability of MRARC in handling various complex noises in reality. Using MRARC as a general platform, we also develop four novel RC methods for unimodal and multimodal face recognition, respectively. In addition, we devise a general optimization algorithm for the unified MRARC framework based on the alternating direction method of multipliers (ADMM) and half-quadratic theory. The experiments on real-world data validate the efficacy of MRARC for robust face recognition.

[37]  arXiv:1711.05862 [pdf, other]
Title: Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines
Subjects: Computer Vision and Pattern Recognition (cs.CV)

This paper presents an approach for real-time training and testing for document image classification. In production environments, it is crucial to perform accurate and (time-)efficient training. Existing deep learning approaches for classifying documents do not meet these requirements, as they require much time for training and fine-tuning the deep architectures. Motivated from Computer Vision, we propose a two-stage approach. The first stage trains a deep network that works as feature extractor and in the second stage, Extreme Learning Machines (ELMs) are used for classification. The proposed approach outperforms all previously reported structural and deep learning based methods with a final accuracy of 83.24% on Tobacco-3482 dataset, leading to a relative error reduction of 25% when compared to a previous Convolutional Neural Network (CNN) based approach (DeepDocClassifier). More importantly, the training time of the ELM is only 1.176 seconds and the overall prediction time for 2,482 images is 3.066 seconds. As such, this novel approach makes deep learning-based document classification suitable for large-scale real-time applications.

[38]  arXiv:1711.05864 [pdf, other]
Title: Hidden Markov Random Field Iterative Closest Point
Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)

When registering point clouds resolved from an underlying 2-D pixel structure, such as those resulting from structured light and flash LiDAR sensors, or stereo reconstruction, it is expected that some points in one cloud do not have corresponding points in the other cloud, and that these would occur together, such as along an edge of the depth map. In this work, a hidden Markov random field model is used to capture this prior within the framework of the iterative closest point algorithm. The EM algorithm is used to estimate the distribution parameters and the hidden component memberships. Experiments are presented demonstrating that this method outperforms several other outlier rejection methods when the point clouds have low or moderate overlap.

[39]  arXiv:1711.05865 [pdf]
Title: Pricing Football Players using Neural Networks
Authors: Sourya Dey
Comments: 10 pages technical report
Subjects: Learning (cs.LG)

We designed a multilayer perceptron neural network to predict the price of a football (soccer) player using data on more than 15,000 players from the football simulation video game FIFA 2017. The network was optimized by experimenting with different activation functions, number of neurons and layers, learning rate and its decay, Nesterov momentum based stochastic gradient descent, L2 regularization, and early stopping. Simultaneous exploration of various aspects of neural network training is performed and their trade-offs are investigated. Our final model achieves a top-5 accuracy of 87.2% among 119 pricing categories, and places any footballer within 6.32% of his actual price on average.

[40]  arXiv:1711.05879 [pdf, other]
Title: (geo)graphs - Complex Networks as a shapefile of nodes and a shapefile of edges for different applications
Subjects: Other Computer Science (cs.OH)

Spatial dependency and spatial embedding are basic physical properties of many phenomena modeled by networks. The most indicated computational environment to deal with spatial information is to use Georeferenced Information System (GIS) and Geographical Database Management Systems (GDBMS). Several models have been proposed in this direction, however there is a gap in the literature in generic frameworks for working with Complex Networks in GIS/GDBMS environments. Here we introduce the concept of (geo)graphs: graphs in which the nodes have a known geographical location and the edges have spatial dependence. We present case studies and two open source softwares (GIS4GRAPH and GeoCNet) that indicate how to retrieve networks from GIS data and how to represent networks over GIS data by using (geo)graphs.

[41]  arXiv:1711.05885 [pdf, other]
Title: Crowdsourcing Question-Answer Meaning Representations
Comments: 8 pages, 6 figures, 2 tables
Subjects: Computation and Language (cs.CL)

We introduce Question-Answer Meaning Representations (QAMRs), which represent the predicate-argument structure of a sentence as a set of question-answer pairs. We also develop a crowdsourcing scheme to show that QAMRs can be labeled with very little training, and gather a dataset with over 5,000 sentences and 100,000 questions. A detailed qualitative analysis demonstrates that the crowd-generated question-answer pairs cover the vast majority of predicate-argument relationships in existing datasets (including PropBank, NomBank, QA-SRL, and AMR) along with many previously under-resourced ones, including implicit arguments and relations. The QAMR data and annotation code is made publicly available to enable future work on how best to model these complex phenomena.

[42]  arXiv:1711.05887 [pdf, other]
Title: On Analyzing Job Hop Behavior and Talent Flow Networks
Journal-ref: ICDM Data Science for Human Capital Management, 2017
Subjects: Social and Information Networks (cs.SI); Applications (stat.AP)

Analyzing job hopping behavior is important for the understanding of job preference and career progression of working individuals. When analyzed at the workforce population level, job hop analysis helps to gain insights of talent flow and organization competition. Traditionally, surveys are conducted on job seekers and employers to study job behavior. While surveys are good at getting direct user input to specially designed questions, they are often not scalable and timely enough to cope with fast-changing job landscape. In this paper, we present a data science approach to analyze job hops performed by about 490,000 working professionals located in a city using their publicly shared profiles. We develop several metrics to measure how much work experience is needed to take up a job and how recent/established the job is, and then examine how these metrics correlate with the propensity of hopping. We also study how job hop behavior is related to job promotion/demotion. Finally, we perform network analyses at the job and organization levels in order to derive insights on talent flow as well as job and organizational competitiveness.

[43]  arXiv:1711.05890 [pdf, other]
Title: Occlusion Aware Unsupervised Learning of Optical Flow
Subjects: Computer Vision and Pattern Recognition (cs.CV)

It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised counterpart. Occlusion and large motion are some of the major factors that limit the current unsupervised learning of optical flow methods. In this work we introduce a new method which models occlusion explicitly and a new warping way that facilitates the learning of large motion. Our method shows promising results on Flying Chairs, MPI-Sintel and KITTI benchmark datasets. Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.

[44]  arXiv:1711.05893 [pdf, other]
Title: On Communication Complexity of Classification Problems
Subjects: Learning (cs.LG); Computational Complexity (cs.CC); Information Theory (cs.IT)

This work introduces a model of distributed learning in the spirit of Yao's communication complexity model. We consider a two-party setting, where each of the players gets a list of labelled examplesand they communicate in order to jointly perform some learning task. To naturally fit into the framework of learning theory, we allow the players to send each other labelled examples, where each example costs one unit of communication. This model can also be thought of as a distributed version of sample compression schemes.
We study several fundamental questions in this model. For example, we define the analogues of the complexity classes P, NP and coNP, and show that in this model P equals the intersection of NP and coNP. The proof does not seem to follow from the analogous statement in classical communication complexity; in particular, our proof uses different techniques, including boosting and metric properties of VC classes.
This framework allows to prove, in the context of distributed learning, unconditional separations between various learning contexts, like realizable versus agnostic learning, and proper versus improper learning. The proofs here are based on standard ideas from communication complexity as well as learning theory and geometric constructions in Euclidean space. As a corollary, we also obtain lower bounds that match the performance of algorithms from previous works on distributed classification.

[45]  arXiv:1711.05900 [pdf, ps, other]
Title: Using Noisy Extractions to Discover Causal Knowledge
Subjects: Artificial Intelligence (cs.AI)

Knowledge bases (KB) constructed through information extraction from text play an important role in query answering and reasoning. In this work, we study a particular reasoning task, the problem of discovering causal relationships between entities, known as causal discovery. There are two contrasting types of approaches to discovering causal knowledge. One approach attempts to identify causal relationships from text using automatic extraction techniques, while the other approach infers causation from observational data. However, extractions alone are often insufficient to capture complex patterns and full observational data is expensive to obtain. We introduce a probabilistic method for fusing noisy extractions with observational data to discover causal knowledge. We propose a principled approach that uses the probabilistic soft logic (PSL) framework to encode well-studied constraints to recover long-range patterns and consistent predictions, while cheaply acquired extractions provide a proxy for unseen observations. We apply our method gene regulatory networks and show the promise of exploiting KB signals in causal discovery, suggesting a critical, new area of research.

[46]  arXiv:1711.05905 [pdf, other]
Title: Using experimental game theory to transit human values to ethical AI
Comments: 6 pages, 8 figures
Subjects: Artificial Intelligence (cs.AI)

Knowing the reflection of game theory and ethics, we develop a mathematical representation to bridge the gap between the concepts in moral philosophy (e.g., Kantian and Utilitarian) and AI ethics industry technology standard (e.g., IEEE P7000 standard series for Ethical AI). As an application, we demonstrate how human value can be obtained from the experimental game theory (e.g., trust game experiment) so as to build an ethical AI. Moreover, an approach to test the ethics (rightness or wrongness) of a given AI algorithm by using an iterated Prisoner's Dilemma Game experiment is discussed as an example. Compared with existing mathematical frameworks and testing method on AI ethics technology, the advantages of the proposed approach are analyzed.

[47]  arXiv:1711.05908 [pdf, other]
Title: NISP: Pruning Networks using Neuron Importance Score Propagation
Subjects: Computer Vision and Pattern Recognition (cs.CV)

To reduce the significant redundancy in deep Convolutional Neural Networks (CNNs), most existing methods prune neurons by only considering statistics of an individual layer or two consecutive layers (e.g., prune one layer to minimize the reconstruction error of the next layer), ignoring the effect of error propagation in deep networks. In contrast, we argue that it is essential to prune neurons in the entire neuron network jointly based on a unified goal: minimizing the reconstruction error of important responses in the "final response layer" (FRL), which is the second-to-last layer before classification, for a pruned network to retrain its predictive power. Specifically, we apply feature ranking techniques to measure the importance of each neuron in the FRL, and formulate network pruning as a binary integer optimization problem and derive a closed-form solution to it for pruning neurons in earlier layers. Based on our theoretical analysis, we propose the Neuron Importance Score Propagation (NISP) algorithm to propagate the importance scores of final responses to every neuron in the network. The CNN is pruned by removing neurons with least importance, and then fine-tuned to retain its predictive power. NISP is evaluated on several datasets with multiple CNN models and demonstrated to achieve significant acceleration and compression with negligible accuracy loss.

[48]  arXiv:1711.05909 [pdf]
Title: Social Computing Based Analysis on Monogamous Marriage Puzzle of Human
Subjects: Social and Information Networks (cs.SI)

Most of the mammal species hold polygynous mating systems. The majority of the marriage systems of mankind were also polygynous over civilized history, however, socially imposed monogamy gradually prevails throughout the world. This is difficult to understand because those mostly influential in society are themselves benefitted from polygyny. Actually, the puzzle of monogamous marriage could be explained by a simple mechanism, which lies in the sexual selection dynamics of civilized human societies, driven by wealth redistribution. The discussions in this paper are mainly based on the approach of social computing, with a combination of both experimental and analytical analysis.

[49]  arXiv:1711.05912 [pdf, ps, other]
Title: On Channel Reciprocity to Activate Uplink Channel Training for Downlink Data Transmission
Comments: 6 pages, 3 figures, submitted to IEEE Int. Conf. Commun. (ICC) 2018
Subjects: Information Theory (cs.IT)

We determine, for the first time, the requirement on channel reciprocity to activate uplink channel training, instead of downlink channel training, to achieve a higher data rate for the downlink transmission from a multi-antenna base station to a single-antenna user. To this end, we first derive novel closed-form expressions for the lower bounds on the data rates achieved by these two channel training strategies by considering the impact of finite blocklength. The performance comparison result of these two strategies is determined by the amount of channel reciprocity that is utilized in the uplink channel training. We then derive an approximated but analytical expression for the minimum channel reciprocity that enables the uplink channel training to outperform the downlink channel training. Through numerical results, we demonstrate that this minimum channel reciprocity decreases as the blocklength decreases or the number of transmit antennas increases, which shows the necessity and benefits of activating the uplink channel training for shortpacket communications with massive transmit antennas. This work provides pivotal and unprecedented guidelines on choosing channel training strategies and channel reciprocity calibrations in practice.

[50]  arXiv:1711.05914 [pdf, other]
Title: How Generative Adversarial Nets and its variants Work: An Overview of GAN
Subjects: Learning (cs.LG)

Generative Adversarial Networks gets wide attention in machine learning field because of its massive potential to learn high dimensional, complex real data. Specifically, it does not need to do further distribution assumption and can simply infer real-like samples from latent space. This powerful property leads GAN to be applied various applications such as image synthesis, image attribute editing and semantically decomposing of image. In this review paper, we look into details of GAN that firstly show how it operates and fundamental meaning of objective functions and point to GAN variants applied to vast amount of tasks.

[51]  arXiv:1711.05917 [pdf, other]
Title: Optimal Load Balancing in Millimeter Wave Cellular Heterogeneous Networks
Comments: 7 pages, 5 figures, submitted to ICC 2018
Subjects: Information Theory (cs.IT)

In this paper, we propose a novel and effective approach to optimizing the load balancing in a millimeter wave (mmWave) cellular heterogeneous network (HetNet) with a macro-tier and a micro-tier. The unique characteristics of mmWave transmission are incorporated into the network by adopting the Poisson point process (PPP) for base station (BS) location, the line-of-sight (LoS) ball model for mmWave links, the sectored antenna model for key antenna array characteristics, and Nakagami-$m$ fading for wireless channels. To reduce the load of macro-tier BSs, we consider a bias factor $A_{s}$ in the network for offloading user equipments (UEs) to micro-tier BSs. For this network, we first analyze the loads of macro- and micro-tier BSs. Then we derive a new expression for the rate coverage probability of the network, based on which the optimal $A_{s}$ maximizing the rate coverage probability is found. Through numerical results, we demonstrate the correctness of our analysis and the validity of the optimal $A_{s}$. Importantly, the optimal $A_{s}$ can bring a profound improvement in the rate coverage probability relative to a fixed $A_{s}$. Furthermore, we evaluate the impact of various network parameters, e.g., the densities and the beamwidths of BSs, on the rate coverage probability and the optimal $A_{s}$, offering valuable guidelines into practical mmWave HetNet design.

[52]  arXiv:1711.05918 [pdf, other]
Title: Priming Neural Networks
Subjects: Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG)

Visual priming is known to affect the human visual system to allow detection of scene elements, even those that may have been near unnoticeable before, such as the presence of camouflaged animals. This process has been shown to be an effect of top-down signaling in the visual system triggered by the said cue. In this paper, we propose a mechanism to mimic the process of priming in the context of object detection and segmentation. We view priming as having a modulatory, cue dependent effect on layers of features within a network. Our results show how such a process can be complementary to, and at times more effective than simple post-processing applied to the output of the network, notably so in cases where the object is hard to detect such as in severe noise. Moreover, we find the effects of priming are sometimes stronger when early visual layers are affected. Overall, our experiments confirm that top-down signals can go a long way in improving object detection and segmentation.

[53]  arXiv:1711.05919 [pdf, other]
Title: Learning Deeply Supervised Visual Descriptors for Dense Monocular Reconstruction
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to ambiguous matches at texture-less regions when performing dense reconstruction due to the aperture problem. In this work, we explore the use of learned features for the matching task in dense monocular reconstruction. We propose a novel convolutional neural network (CNN) architecture along with a deeply supervised feature learning scheme for pixel-wise regression of visual descriptors from an image which are best suited for dense monocular SLAM. In particular, our learning scheme minimizes a multi-view matching cost-volume loss with respect to the regressed features at multiple stages within the network, for explicitly learning contextual features that are suitable for dense matching between images captured by a moving monocular camera along the epipolar line. We utilize the learned features from our model for depth estimation inside a real-time dense monocular SLAM framework, where photometric error is replaced by our learned descriptor error. Our evaluation on several challenging indoor scenes demonstrate greatly improved accuracy in dense reconstructions of the well celebrated dense SLAM systems like DTAM, without compromising their real-time performance.

[54]  arXiv:1711.05928 [pdf, ps, other]
Title: Budget-Constrained Multi-Armed Bandits with Multiple Plays
Comments: 20 pages
Subjects: Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)

We study the multi-armed bandit problem with multiple plays and a budget constraint for both the stochastic and the adversarial setting. At each round, exactly $K$ out of $N$ possible arms have to be played (with $1\leq K \leq N$). In addition to observing the individual rewards for each arm played, the player also learns a vector of costs which has to be covered with an a-priori defined budget $B$. The game ends when the sum of current costs associated with the played arms exceeds the remaining budget.
Firstly, we analyze this setting for the stochastic case, for which we assume each arm to have an underlying cost and reward distribution with support $[c_{\min}, 1]$ and $[0, 1]$, respectively. We derive an Upper Confidence Bound (UCB) algorithm which achieves $O(NK^4 \log B)$ regret.
Secondly, for the adversarial case in which the entire sequence of rewards and costs is fixed in advance, we derive an upper bound on the regret of order $O(\sqrt{NB\log(N/K)})$ utilizing an extension of the well-known $\texttt{Exp3}$ algorithm. We also provide upper bounds that hold with high probability and a lower bound of order $\Omega((1 - K/N)^2 \sqrt{NB/K})$.

[55]  arXiv:1711.05929 [pdf, other]
Title: Defense against Universal Adversarial Perturbations
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Recent advances in Deep Learning show the existence of image-agnostic quasi-imperceptible perturbations that when applied to `any' image can fool a state-of-the-art network classifier to change its prediction about the image label. These `Universal Adversarial Perturbations' pose a serious threat to the success of Deep Learning in practice. We present the first dedicated framework to effectively defend the networks against such perturbations. Our approach learns a Perturbation Rectifying Network (PRN) as `pre-input' layers to a targeted model, such that the targeted model needs no modification. The PRN is learned from real and synthetic image-agnostic perturbations, where an efficient method to compute the latter is also proposed. A perturbation detector is separately trained on the Discrete Cosine Transform of the input-output difference of the PRN. A query image is first passed through the PRN and verified by the detector. If a perturbation is detected, the output of the PRN is used for label prediction instead of the actual image. A rigorous evaluation shows that our framework can defend the network classifiers against unseen adversarial perturbations in the real-world scenarios with up to 97.5% success rate. The PRN also generalizes well in the sense that training for one targeted network defends another network with a comparable success rate.

[56]  arXiv:1711.05932 [pdf, other]
Title: A Design-Time/Run-Time Application Mapping Methodology for Predictable Execution Time in MPSoCs
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Multiagent Systems (cs.MA); Networking and Internet Architecture (cs.NI); Systems and Control (cs.SY)

Executing multiple applications on a single MPSoC brings the major challenge of satisfying multiple quality requirements regarding real-time, energy, etc. Hybrid application mapping denotes the combination of design-time analysis with run-time application mapping. In this article, we present such a methodology, which comprises a design space exploration coupled with a formal performance analysis. This results in several resource reservation configurations, optimized for multiple objectives, with verified real-time guarantees for each individual application. The Pareto-optimal configurations are handed over to run-time management which searches for a suitable mapping according to this information. To provide any real-time guarantees, the performance analysis needs to be composable and the influence of the applications on each other has to be bounded. We achieve this either by spatial or a novel temporal isolation for tasks and by exploiting composable NoCs. With the proposed temporal isolation, tasks of different applications can be mapped to the same resource while with spatial isolation, one computing resource can be exclusively used by only one application. The experiments reveal that the success rate in finding feasible application mappings can be increased by the proposed temporal isolation by up to 30% and energy consumption can be reduced compared to spatial isolation.

[57]  arXiv:1711.05934 [pdf, other]
Title: Enhanced Attacks on Defensively Distilled Deep Neural Networks
Subjects: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR); Learning (cs.LG)

Deep neural networks (DNNs) have achieved tremendous success in many tasks of machine learning, such as the image classification. Unfortunately, researchers have shown that DNNs are easily attacked by adversarial examples, slightly perturbed images which can mislead DNNs to give incorrect classification results. Such attack has seriously hampered the deployment of DNN systems in areas where security or safety requirements are strict, such as autonomous cars, face recognition, malware detection. Defensive distillation is a mechanism aimed at training a robust DNN which significantly reduces the effectiveness of adversarial examples generation. However, the state-of-the-art attack can be successful on distilled networks with 100% probability. But it is a white-box attack which needs to know the inner information of DNN. Whereas, the black-box scenario is more general. In this paper, we first propose the epsilon-neighborhood attack, which can fool the defensively distilled networks with 100% success rate in the white-box setting, and it is fast to generate adversarial examples with good visual quality. On the basis of this attack, we further propose the region-based attack against defensively distilled DNNs in the black-box setting. And we also perform the bypass attack to indirectly break the distillation defense as a complementary method. The experimental results show that our black-box attacks have a considerable success rate on defensively distilled networks.

[58]  arXiv:1711.05938 [pdf, other]
Title: When Mobile Blockchain Meets Edge Computing: Challenges and Applications
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC)

Blockchain, as the backbone technology of the current popular Bitcoin digital currency, has become a promising decentralized approach for resource and transaction management. Although blockchain has been widely adopted in many applications, e.g., finance, healthcare, and logistics, its application in mobile environments is still limited. This is due to the fact that blockchain users need to solve preset proof-of-work puzzles to add new transactions to the blockchain. Solving the proof-of-work, however, consumes substantial resources in terms of CPU time and energy, which is not suitable for resource-limited mobile devices. To facilitate blockchain applications in future mobile Internet of Things systems, multiple access mobile edge computing appears to be an auspicious option to solve the proof-of-work puzzles for mobile users. We first introduce a novel concept of edge computing for mobile blockchain. Then, we introduce an economic approach for edge computing resource management. Moreover, a demonstrative prototype of mobile edge computing enabled blockchain systems is presented with experimental results to justify the proposed concept.

[59]  arXiv:1711.05941 [pdf, other]
Title: Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Human skeleton joints are popular for action analysis since they can be easily extracted from videos to discard background noises. However, current skeleton representations do not fully benefit from machine learning with CNNs. We propose "Skepxels" a spatio-temporal representation for skeleton sequences to fully exploit the "local" correlations between joints using the 2D convolution kernels of CNN. We transform skeleton videos into images of flexible dimensions using Skepxels and develop a CNN-based framework for effective human action recognition using the resulting images. Skepxels encode rich spatio-temporal information about the skeleton joints in the frames by maximizing a unique distance metric, defined collaboratively over the distinct joint arrangements used in the skeletal image. Moreover, they are flexible in encoding compound semantic notions such as location and speed of the joints. The proposed action recognition exploits the representation in a hierarchical manner by first capturing the micro-temporal relations between the skeleton joints with the Skepxels and then exploiting their macro-temporal relations by computing the Fourier Temporal Pyramids over the CNN features of the skeletal images. We extend the Inception-ResNet CNN architecture with the proposed method and improve the state-of-the-art accuracy by 4.4% on the large scale NTU human activity dataset. On the medium-sized N-UCLA and UTH-MHAD datasets, our method outperforms the existing results by 5.7% and 9.3% respectively.

[60]  arXiv:1711.05942 [pdf, other]
Title: Learning from Millions of 3D Scans for Large-scale 3D Face Recognition
Comments: 11 pages
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as well as large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the art face recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world face recognition problem.

[61]  arXiv:1711.05944 [pdf, other]
Title: HandSeg: A Dataset for Hand Segmentation from Depth Images
Subjects: Computer Vision and Pattern Recognition (cs.CV)

We introduce a large-scale RGBD hand segmentation dataset, with detailed and automatically generated high-quality ground-truth annotations. Existing real-world datasets are limited in quantity due to the difficulty in manually annotating ground-truth labels. By leveraging a pair of brightly colored gloves and an RGBD camera, we propose an acquisition pipeline that eases the task of annotating very large datasets with minimal human intervention. We then quantify the importance of a large annotated dataset in this domain, and compare the performance of existing datasets in the training of deep-learning architectures. Finally, we propose a novel architecture employing strided convolution/deconvolutions in place of max-pooling and unpooling layers. Our variant outperforms baseline architectures while remaining computationally efficient at inference time. Source and datasets will be made publicly available.

[62]  arXiv:1711.05953 [pdf, other]
Title: 3D Face Reconstruction from Light Field Images: A Model-free Approach
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Reconstructing 3D facial geometry from a single RGB image has recently instigated wide research interest. However, it is still an ill-posed problem and most methods rely on prior models hence undermining the accuracy of the recovered 3D faces. In this paper, we exploit the Epipolar Plane Images (EPI) obtained from light field cameras and learn CNN models that recover horizontal and vertical 3D facial curves from the respective horizontal and vertical EPIs. Our 3D face reconstruction network (FaceLFnet) comprises a densely connected architecture to learn accurate 3D facial curves from low resolution EPIs. To train the proposed FaceLFnets from scratch, we synthesize photo-realistic light field images from 3D facial scans. The curve by curve 3D face estimation approach allows the networks to learn from only 14K images of 80 identities, which still comprises over 11 Million EPIs/curves. The estimated facial curves are merged into a single pointcloud to which a surface is fitted to get the final 3D face. Our method is model-free, requires only a few training samples to learn FaceLFnet and can reconstruct 3D faces with high accuracy from single light field images under varying poses, expressions and lighting conditions. Comparison on the BU-3DFE and BU-4DFE datasets show that our method reduces reconstruction errors by over 20% compared to recent state of the art.

[63]  arXiv:1711.05954 [pdf, other]
Title: Zero-Annotation Object Detection with Web Knowledge Transfer
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Object detection is one of the major problems in computer vision, and has been extensively studied. Most of of the existing detection works rely on labor-intensive supervisions, such as ground truth bounding boxes of objects or at least image-level annotations. On the contrary, we propose an object detection method that does not require any form of supervisions on target tasks, by exploiting freely available web images. In order to facilitate effective knowledge transfer from web images, we introduce a multi-instance multi-label domain adaption learning framework with two key innovations. First of all, we propose an instance-level adversarial domain adaptation network with attention on foreground objects to transfer the object appearances from web domain to target domain. Second, to preserve the class-specific semantic structure of transferred object features, we propose a simultaneous transfer mechanism to transfer the supervision across domains through pseudo strong label generation. With our end-to-end framework that simultaneously learns a weakly supervised detector and transfers knowledge across domains, we achieved significant improvements over baseline methods on the benchmark datasets.

[64]  arXiv:1711.05959 [pdf, other]
Title: Less-forgetful Learning for Domain Expansion in Deep Neural Networks
Comments: 8 pages, accepted to AAAI 2018
Subjects: Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

Expanding the domain that deep neural network has already learned without accessing old domain data is a challenging task because deep neural networks forget previously learned information when learning new data from a new domain. In this paper, we propose a less-forgetful learning method for the domain expansion scenario. While existing domain adaptation techniques solely focused on adapting to new domains, the proposed technique focuses on working well with both old and new domains without needing to know whether the input is from the old or new domain. First, we present two naive approaches which will be problematic, then we provide a new method using two proposed properties for less-forgetful learning. Finally, we prove the effectiveness of our method through experiments on image classification tasks. All datasets used in the paper, will be released on our website for someone's follow-up study.

[65]  arXiv:1711.05962 [pdf, other]
Title: Beagle: Automated Extraction and Interpretation of Visualizations from the Web
Comments: 5 pages
Subjects: Human-Computer Interaction (cs.HC)

"How common is interactive visualization on the web?" "What is the most popular visualization design?" "How prevalent are pie charts really?" These questions intimate the role of interactive visualization in the real (online) world. In this paper, we present our approach (and findings) to answering these questions. First, we introduce Beagle, which mines the web for SVG-based visualizations and automatically classifies them by type (i.e., bar, pie, etc.). With Beagle, we extract over 41,000 visualizations across five different tools and repositories, and classify them with 86% accuracy, across 24 visualization types. Given this visualization collection, we study usage across tools. We find that most visualizations fall under four types: bar charts, line charts, scatter charts, and geographic maps. Though controversial, pie charts are relatively rare in practice. Our findings also indicate that users may prefer tools that emphasize a succinct set of visualization types, and provide diverse expert visualization examples.

[66]  arXiv:1711.05969 [pdf, ps, other]
Title: Physical-Layer Schemes for Wireless Coded Caching
Comments: 25 pages, 14 figures. This manuscript is the extended journal version of the ISIT 2017 conference article available at arXiv:1701.02979 [cs.IT]
Subjects: Information Theory (cs.IT); Networking and Internet Architecture (cs.NI)

We investigate the potentials of applying the coded caching paradigm in wireless networks. In order to do this, we investigate physical layer schemes for downlink transmission from a multiantenna transmitter to several cache-enabled users. As the baseline scheme we consider employing coded caching on top of max-min fair multicasting, which is shown to be far from optimal at high SNR values. Our first proposed scheme, which is near-optimal in terms of DoF, is the natural extension of multiserver coded caching to Gaussian channels. As we demonstrate, its finite SNR performance is not satisfactory, and thus we propose a new scheme in which the linear combination of messages is implemented in the finite field domain, and the one-shot precoding for the MISO downlink is implemented in the complex field. While this modification results in the same near-optimal DoF performance, we show that this leads to significant performance improvement at finite SNR. Finally, we extend our scheme to the previously considered cache-enabled interference channels, and moreover, we provide an Ergodic rate analysis of our scheme. Our results convey the important message that although directly translating schemes from the network coding ideas to wireless networks may work well at high SNR values, careful modifications need to be considered for acceptable finite SNR performance.

[67]  arXiv:1711.05971 [pdf, other]
Title: Learning to Find Good Correspondences
Subjects: Computer Vision and Pattern Recognition (cs.CV)

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while imbuing it with global information, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data.

[68]  arXiv:1711.05979 [pdf, other]
Title: Performance Modeling and Evaluation of Distributed Deep Learning Frameworks on GPUs
Comments: 11 pages
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC)

Deep learning frameworks have been widely deployed on GPU servers for deep learning applications in both academia and industry. In the training of deep neural networks (DNNs), there are many standard processes or algorithms, such as convolution and stochastic gradient descent (SGD), but the running performance of different frameworks might be different even running the same deep model on the same GPU hardware. In this paper, we evaluate the running performance of four state-of-the-art distributed deep learning frameworks (i.e., Caffe-MPI, CNTK, MXNet and TensorFlow) over single-GPU, multi-GPU and multi-node environments. We first build performance models of standard processes in training DNNs with SGD, and then we benchmark the running performance of these frameworks with three popular convolutional neural networks (i.e., AlexNet, GoogleNet and ResNet-50), after that we analyze what factors that results in the performance gap among these four frameworks. Through both analytical and experimental analysis, we identify bottlenecks and overheads which could be further optimized. The main contribution is two-fold. First, the testing results provide a reference for end users to choose the proper framework for their own scenarios. Second, the proposed performance models and the detailed analysis provide further optimization directions in both algorithmic design and system configuration.

[69]  arXiv:1711.05993 [pdf, other]
Title: On evolutionary selection of blackjack strategies
Authors: Mikhail Goykhman
Comments: Code is available here: this https URL
Subjects: Neural and Evolutionary Computing (cs.NE)

We apply the approach of evolutionary programming to the problem of optimization of the blackjack basic strategy. We demonstrate that the population of initially random blackjack strategies evolves and saturates to a profitable performance in about one hundred generations. The resulting strategy resembles the known blackjack basic strategies in the specifics of its prescriptions, and has a similar performance. We also study evolution of the population of strategies initialized to the Thorp's basic strategy.

[70]  arXiv:1711.05994 [pdf, ps, other]
Title: Singular value automata and approximate minimization
Subjects: Formal Languages and Automata Theory (cs.FL)

The present paper uses spectral theory of linear operators to construct approximately minimal realizations of weighted languages. Our new contributions are: (i) a new algorithm for the SVD decomposition of infinite Hankel matrices based on their representation in terms of weighted automata, (ii) a new canonical form for weighted automata arising from the SVD of its corresponding Hankel matrix and (iii) an algorithm to construct approximate minimizations of given weighted automata by truncating the canonical form. We give bounds on the quality of our approximation.

[71]  arXiv:1711.05997 [pdf, other]
Title: Towards a Cloud-based Architecture for Visualization and Augmented Reality to Support Collaboration in Manufacturing Automation
Subjects: Software Engineering (cs.SE)

In this report, we present our work in visualization and augmented reality technologies supporting collaboration in manufacturing automation. Our approach is based on (i) analysis based on spatial models of automation environments, (ii) next-generation controllers based on single board computers, (iii) cloud-, service- and web-based technologies and (iv) an emphasis on experimental development using real automation equipment. The contribution of this paper is the documentation of two new demonstrators, one for distributed viewing of 3D scans of factory environments, and another for real time augmented reality display of the status of a manufacturing plant, each based on technologies under development in our lab and in particular applied to a mini-factory.

[72]  arXiv:1711.05998 [pdf, other]
Title: Superpixel clustering with deep features for unsupervised road segmentation
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Vision-based autonomous driving requires classifying each pixel as corresponding to road or not, which can be addressed using semantic segmentation. Semantic segmentation works well when used with a fully supervised model, but in practice, the required work of creating pixel-wise annotations is very expensive. Although weakly supervised segmentation addresses this issue, most methods are not designed for road segmentation. In this paper, we propose a novel approach to road segmentation that eliminates manual annotation and effectively makes use of road-specific cues. Our method has better performance than other weakly supervised methods and achieves 98% of the performance of a fully supervised method, showing the feasibility of road segmentation for autonomous driving without tedious and costly manual annotation.

[73]  arXiv:1711.06000 [pdf, ps, other]
Title: Empirical model for combinatorial data center network switch design
Comments: 4 pages
Subjects: Networking and Internet Architecture (cs.NI)

Data centers require high-performance network equipment that consume low power and support high bandwidth requirements. In this context, a combinatorial approach was proposed to design data center network (DCN) equipment from a library of components in \cite{infocom}. This library includes power splitter, wavelength multiplexers, reconfigurable add-drop multiplexers and optical amplifiers. When interconnecting optical components, it must be ensured that the resultant network supports specified target bit-error-rates (typically, at most $10^{-12}$). This paper reports experiment conducted on component interconnections and their computed bit-error-rates. From the experimental analysis, it was observed that the desired objective can be decided by considering a zeroth-order threshold for optical power at the receiver and before the amplifier. This paves way for the theoretical evaluation of several other such designs using this empirically derived model.

[74]  arXiv:1711.06004 [pdf, other]
Title: Remedies against the Vocabulary Gap in Information Retrieval
Comments: PhD thesis
Subjects: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Search engines rely heavily on term-based approaches that represent queries and documents as bags of words. Text---a document or a query---is represented by a bag of its words that ignores grammar and word order, but retains word frequency counts. When presented with a search query, the engine then ranks documents according to their relevance scores by computing, among other things, the matching degrees between query and document terms. While term-based approaches are intuitive and effective in practice, they are based on the hypothesis that documents that exactly contain the query terms are highly relevant regardless of query semantics. Inversely, term-based approaches assume documents that do not contain query terms as irrelevant. However, it is known that a high matching degree at the term level does not necessarily mean high relevance and, vice versa, documents that match null query terms may still be relevant. Consequently, there exists a vocabulary gap between queries and documents that occurs when both use different words to describe the same concepts. It is the alleviation of the effect brought forward by this vocabulary gap that is the topic of this dissertation. More specifically, we propose (1) methods to formulate an effective query from complex textual structures and (2) latent vector space models that circumvent the vocabulary gap in information retrieval.

[75]  arXiv:1711.06006 [pdf, other]
Title: Hindsight policy gradients
Comments: Accepted to NIPS 2017 Hierarchical Reinforcement Learning Workshop
Subjects: Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Robotics (cs.RO)

Goal-conditional policies allow reinforcement learning agents to pursue specific goals during different episodes. In addition to their potential to generalize desired behavior to unseen goals, such policies may also help in defining options for arbitrary subgoals, enabling higher-level planning. While trying to achieve a specific goal, an agent may also be able to exploit information about the degree to which it has achieved alternative goals. Reinforcement learning agents have only recently been endowed with such capacity for hindsight, which is highly valuable in environments with sparse rewards. In this paper, we show how hindsight can be introduced to likelihood-ratio policy gradient methods, generalizing this capacity to an entire class of highly successful algorithms. Our preliminary experiments suggest that hindsight may increase the sample efficiency of policy gradient methods.

[76]  arXiv:1711.06011 [pdf, other]
Title: Parametric Manifold Learning Via Sparse Multidimensional Scaling
Comments: 11 pages, 8 Figures
Subjects: Computer Vision and Pattern Recognition (cs.CV)

We propose a metric-learning framework for computing distance-preserving maps that generate low-dimensional embeddings for a certain class of manifolds. We employ Siamese networks to solve the problem of least squares multidimensional scaling for generating mappings that preserve geodesic distances on the manifold. In contrast to previous parametric manifold learning methods we show a substantial reduction in training effort enabled by the computation of geodesic distances in a farthest point sampling strategy. Additionally, the use of a network to model the distance-preserving map reduces the complexity of the multidimensional scaling problem and leads to an improved non-local generalization of the manifold compared to analogous non-parametric counterparts. We demonstrate our claims on point-cloud data and on image manifolds and show a numerical analysis of our technique to facilitate a greater understanding of the representational power of neural networks in modeling manifold data.

[77]  arXiv:1711.06012 [pdf, ps, other]
Title: Stability of optimal spherical codes
Subjects: Information Theory (cs.IT)

For many extremal configurations of points on a sphere, the linear programming approach can be used to show their optimality. In this paper we establish the general framework for showing stability of such configurations and use this framework to prove the stability of the two spherical codes formed by minimal vectors of the lattice $E_8$ and of the Leech lattice.

[78]  arXiv:1711.06014 [pdf, other]
Title: Aerial Anchors Positioning for Reliable RSS-Based Outdoor Localization in Urban Environments
Comments: Submitted to the IEEE Wireless Communication Letters for possible publication
Subjects: Networking and Internet Architecture (cs.NI)

In this letter, the localization of terrestrial nodes when unmanned aerial vehicles (UAVs) are used as base stations is investigated. Particularly, a novel localization scenario based on received signal strength (RSS) from terrestrial nodes is introduced. In contrast to the existing literature, our analysis includes height-dependent path loss exponent and shadowing which results in an optimum UAV altitude for minimum localization error. Furthermore, the Cram\'er-Rao lower bound is derived for the estimated distance which emphasizes, analytically, the existence of an optimal UAV altitude. Our simulation results show that the localization error is decreased from over 300m when using ground-based anchors to 80m when using UAVs flying at the optimal altitude in an urban scenario.

[79]  arXiv:1711.06016 [pdf, other]
Title: A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
Subjects: Computer Vision and Pattern Recognition (cs.CV)

There is a growing trend in studying deep hashing methods for content-based image retrieval (CBIR), where hash functions and binary codes are learnt using deep convolutional neural networks and then the binary codes can be used to do approximate nearest neighbor (ANN) search. All the existing deep hashing papers report their methods' superior performance over the traditional hashing methods according to their experimental results. However, there are serious flaws in the evaluations of existing deep hashing papers: (1) The datasets they used are too small and simple to simulate the real CBIR situation. (2) They did not correctly include the search time in their evaluation criteria, while the search time is crucial in real CBIR systems. (3) The performance of some unsupervised hashing algorithms (e.g., LSH) can easily be boosted if one uses multiple hash tables, which is an important factor should be considered in the evaluation while most of the deep hashing papers failed to do so.
We re-evaluate several state-of-the-art deep hashing methods with a carefully designed experimental setting. Empirical results reveal that the performance of these deep hashing methods are inferior to multi-table IsoH, a very simple unsupervised hashing method. Thus, the conclusions in all the deep hashing papers should be carefully re-examined.

[80]  arXiv:1711.06020 [pdf, ps, other]
Title: Global versus Localized Generative Adversarial Nets
Subjects: Computer Vision and Pattern Recognition (cs.CV)

In this paper, we present a novel localized Generative Adversarial Net (GAN) to learn on the manifold of real data. Compared with the classic GAN that {\em globally} parameterizes a manifold, the Localized GAN (LGAN) uses local coordinate charts to parameterize distinct local geometry of how data points can transform at different locations on the manifold. Specifically, around each point there exists a {\em local} generator that can produce data following diverse patterns of transformations on the manifold. The locality nature of LGAN enables local generators to adapt to and directly access the local geometry without need to invert the generator in a global GAN. Furthermore, it can prevent the manifold from being locally collapsed to a dimensionally deficient tangent subspace by imposing an orthonormality prior between tangents. This provides a geometric approach to alleviating mode collapse at least locally on the manifold by imposing independence between data transformations in different tangent directions. We will also demonstrate the LGAN can be applied to train a robust classifier that prefers locally consistent classification decisions on the manifold, and the resultant regularizer is closely related with the Laplace-Beltrami operator. Our experiments show that the proposed LGANs can not only produce diverse image transformations, but also deliver superior classification performances.

[81]  arXiv:1711.06024 [pdf, other]
Title: Bounding the convergence time of local probabilistic evolution
Comments: 8 pages, 2 figures
Journal-ref: International Conference on Geometric Science of Information. Springer, Cham, 2017
Subjects: Discrete Mathematics (cs.DM)

Isoperimetric inequalities form a very intuitive yet powerful characterization of the connectedness of a state space, that has proven successful in obtaining convergence bounds. Since the seventies they form an essential tool in differential geometry, graph theory and Markov chain analysis. In this paper we use isoperimetric inequalities to construct a bound on the convergence time of any local probabilistic evolution that leaves its limit distribution invariant. We illustrate how this general result leads to new bounds on convergence times beyond the explicit Markovian setting, among others on quantum dynamics.

[82]  arXiv:1711.06025 [pdf, other]
Title: Learning to Compare: Relation Network for Few-Shot Learning
Subjects: Computer Vision and Pattern Recognition (cs.CV)

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning. Extensive experiments on four datasets demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.

[83]  arXiv:1711.06030 [pdf, ps, other]
Title: Sub-committee Approval Voting and Generalised Justified Representation Axioms
Subjects: Computer Science and Game Theory (cs.GT); Artificial Intelligence (cs.AI)

Social choice is replete with various settings including single-winner voting, multi-winner voting, probabilistic voting, multiple referenda, and public decision making. We study a general model of social choice called Sub-Committee Voting (SCV) that simultaneously generalizes these settings. We then focus on sub-committee voting with approvals and propose extensions of the justified representation axioms that have been considered for proportional representation in approval-based committee voting. We study the properties and relations of these axioms. For each of the axioms, we analyse whether a representative committee exists and also examine the complexity of computing and verifying such a committee.

[84]  arXiv:1711.06032 [pdf, other]
Title: Natural Language Guided Visual Relationship Detection
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Reasoning about the relationships between object pairs in images is a crucial task for holistic scene understanding. Most of the existing works treat this task as a pure visual classification task: each type of relationship or phrase is classified as a relation category based on the extracted visual features. However, each kind of relationships has a wide variety of object combination and each pair of objects has diverse interactions. Obtaining sufficient training samples for all possible relationship categories is difficult and expensive. In this work, we propose a natural language guided framework to tackle this problem. We propose to use a generic bi-directional recurrent neural network to predict the semantic connection between the participating objects in the relationship from the aspect of natural language. The proposed simple method achieves the state-of-the-art on the Visual Relationship Detection (VRD) and Visual Genome datasets, especially when predicting unseen relationships (e.g. recall improved from 76.42% to 89.79% on VRD zero-shot testing set).

[85]  arXiv:1711.06035 [pdf, other]
Title: From Algorithmic Black Boxes to Adaptive White Boxes: Declarative Decision-Theoretic Ethical Programs as Codes of Ethics
Comments: 7 pages, 1 figure, submitted
Subjects: Artificial Intelligence (cs.AI)

Ethics of algorithms is an emerging topic in various disciplines such as social science, law, and philosophy, but also artificial intelligence (AI). The value alignment problem expresses the challenge of (machine) learning values that are, in some way, aligned with human requirements or values. In this paper I argue for looking at how humans have formalized and communicated values, in professional codes of ethics, and for exploring declarative decision-theoretic ethical programs (DDTEP) to formalize codes of ethics. This renders machine ethical reasoning and decision-making, as well as learning, more transparent and hopefully more accountable. The paper includes proof-of-concept examples of known toy dilemmas and gatekeeping domains such as archives and libraries.

[86]  arXiv:1711.06039 [pdf, ps, other]
Title: Cloud Data Auditing Using Proofs of Retrievability
Comments: A version has been published as a book chapter in Guide to Security Assurance for Cloud Computing (Springer International Publishing Switzerland 2015)
Subjects: Cryptography and Security (cs.CR)

Cloud servers offer data outsourcing facility to their clients. A client outsources her data without having any copy at her end. Therefore, she needs a guarantee that her data are not modified by the server which may be malicious. Data auditing is performed on the outsourced data to resolve this issue. Moreover, the client may want all her data to be stored untampered. In this chapter, we describe proofs of retrievability (POR) that convince the client about the integrity of all her data.

[87]  arXiv:1711.06041 [pdf, other]
Title: Securing Heterogeneous IoT with Intelligent DDoS Attack Behavior Learning
Comments: Submitted to IEEE Communications Magazine
Subjects: Networking and Internet Architecture (cs.NI)

The rapid increase of diverse Internet of things (IoT) services and devices has raised numerous challenges in terms of connectivity, computation, and security, which networks must face in order to provide satisfactory support. This has led to networks evolving into heterogeneous IoT networking infrastructures characterized by multiple access technologies and mobile edge computing (MEC) capabilities. The heterogeneity of the networks, devices, and services introduces serious vulnerabilities to security attacks, especially distributed denial-of-service (DDoS) attacks, which exploit massive IoT devices to exhaust both network and victim resources. As such, this study proposes MECshield, a localized DDoS prevention framework leveraging MEC power to deploy multiple smart filters at the edge of relevant attack-source/destination networks. The cooperation among the smart filters is supervised by a central controller. The central controller localizes each smart filter by feeding appropriate training parameters into its self-organizing map (SOM) component, based on the attacking behavior. The performance of the MECshield framework is verified using three typical IoT traffic scenarios. The numerical results reveal that MECshield outperforms existing solutions.

[88]  arXiv:1711.06045 [pdf, other]
Title: Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Frame interpolation attempts to synthesise intermediate frames given one or more consecutive video frames. In recent years, deep learning approaches, and in particular convolutional neural networks, have succeeded at tackling low- and high-level computer vision problems including frame interpolation. There are two main pursuits in this line of research, namely algorithm efficiency and reconstruction quality. In this paper, we present a multi-scale generative adversarial network for frame interpolation (FIGAN). To maximise the efficiency of our network, we propose a novel multi-scale residual estimation module where the predicted flow and synthesised frame are constructed in a coarse-to-fine fashion. To improve the quality of synthesised intermediate video frames, our network is jointly supervised at different levels with a perceptual loss function that consists of an adversarial and two content losses. We evaluate the proposed approach using a collection of 60fps videos from YouTube-8m. Our results improve the state-of-the-art accuracy and efficiency, and a subjective visual quality comparable to the best performing interpolation method.

[89]  arXiv:1711.06047 [pdf, other]
Title: Deep Matching Autoencoders
Comments: 10 pages
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicability is thus limited as the paired data assumption is often violated in practice: many tasks have only a small subset of data available with pairing annotation, or even no paired data at all. In this paper we introduce Deep Matching Autoencoders (DMAE), which learn a common latent space and pairing from unpaired multi-modal data. Specifically we formulate this as a cross-domain representation learning and object matching problem. We simultaneously optimise parameters of representation learning auto-encoders and the pairing of unpaired multi-modal data. This framework elegantly spans the full regime from fully supervised, semi-supervised, and unsupervised (no paired data) multi-modal learning. We show promising results in image captioning, and on a new task that is uniquely enabled by our methodology: unsupervised classifier learning.

[90]  arXiv:1711.06055 [pdf, other]
Title: Integrated Face Analytics Networks through Cross-Dataset Hybrid Training
Comments: 10 pages
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Face analytics benefits many multimedia applications. It consists of a number of tasks, such as facial emotion recognition and face parsing, and most existing approaches generally treat these tasks independently, which limits their deployment in real scenarios. In this paper we propose an integrated Face Analytics Network (iFAN), which is able to perform multiple tasks jointly for face analytics with a novel carefully designed network architecture to fully facilitate the informative interaction among different tasks. The proposed integrated network explicitly models the interactions between tasks so that the correlations between tasks can be fully exploited for performance boost. In addition, to solve the bottleneck of the absence of datasets with comprehensive training data for various tasks, we propose a novel cross-dataset hybrid training strategy. It allows "plug-in and play" of multiple datasets annotated for different tasks without the requirement of a fully labeled common dataset for all the tasks. We experimentally show that the proposed iFAN achieves state-of-the-art performance on multiple face analytics tasks using a single integrated model. Specifically, iFAN achieves an overall F-score of 91.15% on the Helen dataset for face parsing, a normalized mean error of 5.81% on the MTFL dataset for facial landmark localization and an accuracy of 45.73% on the BNU dataset for emotion recognition with a single model.

[91]  arXiv:1711.06061 [pdf, other]
Title: An Encoder-Decoder Framework Translating Natural Language to Database Queries
Subjects: Computation and Language (cs.CL)

Machine translation is going through a radical revolution, driven by the explosive development of deep learning techniques using Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In this paper, we consider a special case in machine translation problems, targeting to translate natural language into Structural Query Language (SQL) for data retrieval over relational database. Although generic CNN and RNN learn the grammar structure of SQL when trained with sufficient samples, the accuracy and training efficiency of the model could be dramatically improved, when the translation model is deeply integrated with the grammar rules of SQL. We present a new encoder-decoder framework, with a suite of new approaches, including new semantic features fed into the encoder as well as new grammar-aware states injected into the memory of decoder. These techniques help the neural network focus on understanding semantics of the operations in natural language and save the efforts on SQL grammar learning. The empirical evaluation on real world database and queries show that our approach outperform state-of-the-art solution by a significant margin.

[92]  arXiv:1711.06063 [pdf, ps, other]
Title: On error linear complexity of new generalized cyclotomic binary sequences of period $p^2$
Subjects: Cryptography and Security (cs.CR); Number Theory (math.NT)

We consider the $k$-error linear complexity of a new binary sequence of period $p^2$, proposed in the recent paper "New generalized cyclotomic binary sequences of period $p^2$", by Z. Xiao et al., who calculated the linear complexity of the sequences (Designs, Codes and Cryptography, 2017, https://doi.org/10.1007/s10623-017-0408-7). More exactly, we determine the values of $k$-error linear complexity over $\mathbb{F}_2$ for almost $k>0$ in terms of the theory of Fermat quotients. Results indicate that such sequences have good stability.

[93]  arXiv:1711.06065 [pdf, other]
Title: Automata in the Category of Glued Vector Spaces
Comments: 15 pages, knowledge enriched version of the MFCS 2017 proceedings paper
Subjects: Formal Languages and Automata Theory (cs.FL)

In this paper we adopt a category-theoretic approach to the conception of automata classes enjoying minimization by design. The main instantiation of our construction is a new class of automata that are hybrid between deterministic automata and automata weighted over a field.

[94]  arXiv:1711.06068 [pdf]
Title: The signature of robot action success in EEG signals of a human observer: Decoding and visualization using deep convolutional neural networks
Subjects: Human-Computer Interaction (cs.HC); Learning (cs.LG); Robotics (cs.RO)

The importance of robotic assistive devices grows in our work and everyday life. Cooperative scenarios involving both robots and humans require safe human-robot interaction. One important aspect here is the management of robot errors, including fast and accurate online robot-error detection and correction. Analysis of brain signals from a human interacting with a robot may help identifying robot errors, but accuracies of such analyses have still substantial space for improvement. In this paper we evaluate whether a novel framework based on deep convolutional neural networks (deep ConvNets) could improve the accuracy of decoding robot errors from the EEG of a human observer, both during an object grasping and a pouring task. We show that deep ConvNets reached significantly higher accuracies than both regularized Linear Discriminant Analysis (rLDA) and filter bank common spatial patterns (FB-CSP) combined with rLDA, both widely used EEG classifiers. Deep ConvNets reached mean accuracies of 75% +/- 9 %, rLDA 65% +/- 10% and FB-CSP + rLDA 63% +/- 6% for decoding of erroneous vs. correct trials. Visualization of the time-domain EEG features learned by the ConvNets to decode errors revealed spatiotemporal patterns that reflected differences between the two experimental paradigms. Across subjects, ConvNet decoding accuracies were significantly correlated with those obtained with rLDA, but not CSP, indicating that in the present context ConvNets behaved more 'rLDA-like' (but consistently better), while in a previous decoding study with another task but the same ConvNet architecture, it was found to behave more 'CSP-like'. Our findings thus provide further support for the assumption that deep ConvNets are a versatile addition to the existing toolbox of EEG decoding techniques, and we discuss steps how ConvNet EEG decoding performance could be further optimized.

[95]  arXiv:1711.06073 [pdf, other]
Title: An n-sided polygonal model to calculate the impact of cyber security events
Comments: 16 pages, 5 figures, 2 tables, 11th International Conference on Risks and Security of Internet and Systems, (CRiSIS 2016), Roscoff, France, September 2016
Subjects: Cryptography and Security (cs.CR)

This paper presents a model to represent graphically the impact of cyber events (e.g., attacks, countermeasures) in a polygonal systems of n-sides. The approach considers information about all entities composing an information system (e.g., users, IP addresses, communication protocols, physical and logical resources, etc.). Every axis is composed of entities that contribute to the execution of the security event. Each entity has an associated weighting factor that measures its contribution using a multi-criteria methodology named CARVER. The graphical representation of cyber events is depicted as straight lines (one dimension) or polygons (two or more dimensions). Geometrical operations are used to compute the size (i.e, length, perimeter, surface area) and thus the impact of each event. As a result, it is possible to identify and compare the magnitude of cyber events. A case study with multiple security events is presented as an illustration on how the model is built and computed.

[96]  arXiv:1711.06077 [pdf, other]
Title: The Perception-Distortion Tradeoff
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Image restoration algorithms are typically evaluated by some distortion measure (e.g. PSNR, SSIM) or by human opinion scores that directly quantify perceived perceptual quality. In this paper, we prove mathematically that distortion and perceptual quality are at odds with each other. Specifically, we study the optimal probability for discriminating the outputs of an image restoration algorithm from real images. We show that as the mean distortion decreases, this probability must increase (indicating lower perceptual quality). Surprisingly, this result holds true for any distortion measure (including advanced criteria). However, as we show experimentally, for some measures it is less severe (e.g. distances between VGG features). We also show that generative-adversarial-nets (GANs) provide a principled way to approach the perception-distortion bound. This constitutes theoretical support to their observed success in low-level vision tasks. Based on our analysis, we propose a new methodology for evaluating image restoration methods, and use it to perform an extensive comparison between recent super-resolution algorithms.

[97]  arXiv:1711.06078 [pdf, other]
Title: Two Birds with One Stone: Iteratively Learn Facial Attributes with GANs
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Generating high fidelity identity-preserving faces has a wide range of applications. Although a number of generative models have been developed to tackle this problem, it is still far from satisfying. Recently, Generative adversarial network (GAN) has shown great potential for generating or transforming images of exceptional visual fidelity. In this paper, we propose to train GAN iteratively via regularizing the minmax process with an integrated loss, which includes not only the per-pixel loss but also the perceptual loss. We argue that the perceptual information benefits the output of a high-quality image, while preserving the identity information. In contrast to the existing methods only deal with either image generation or transformation, our proposed iterative architecture can achieve both of them. Experiments on the multi-label facial dataset CelebA demonstrate that the proposed model has excellent performance on recognizing multiple attributes, generating a high-quality image, and transforming image with controllable attributes.

[98]  arXiv:1711.06092 [pdf, other]
Title: Programming the Interactions of Collective Adaptive Systems by Relying on Attribute-based Communication
Subjects: Programming Languages (cs.PL)

Collective adaptive systems are new emerging computational systems consisting of a large number of interacting components and featuring complex behaviour. These systems are usually distributed, heterogeneous, decentralised and interdependent, and are operating in dynamic and possibly unpredictable environments. Finding ways to understand and design these systems and, most of all, to model the interactions of their components, is a difficult but important endeavour. In this article we propose a language-based approach for programming the interactions of collective-adaptive systems by relying on attribute-based communication; a paradigm that permits a group of partners to communicate by considering their run-time properties and capabilities. We introduce AbC, a foundational calculus for attribute-based communication and show how its linguistic primitives can be used to program a complex and sophisticated variant of the well-known problem of Stable Allocation in Content Delivery Networks. Also other interesting case studies, from the realm of collective-adaptive systems, are considered. We also illustrate the expressive power of attribute-based communication by showing the natural encoding of other existing communication paradigms into AbC.

[99]  arXiv:1711.06095 [pdf, other]
Title: Depression Severity Estimation from Multiple Modalities
Comments: 8 pages, 1 figure
Subjects: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)

Depression is a major debilitating disorder which can affect people from all ages. With a continuous increase in the number of annual cases of depression, there is a need to develop automatic techniques for the detection of the presence and extent of depression. In this AVEC challenge we explore different modalities (speech, language and visual features extracted from face) to design and develop automatic methods for the detection of depression. In psychology literature, the PHQ-8 questionnaire is well established as a tool for measuring the severity of depression. In this paper we aim to automatically predict the PHQ-8 scores from features extracted from the different modalities. We show that visual features extracted from facial landmarks obtain the best performance in terms of estimating the PHQ-8 results with a mean absolute error (MAE) of 4.66 on the development set. Behavioral characteristics from speech provide an MAE of 4.73. Language features yield a slightly higher MAE of 5.17. When switching to the test set, our Turn Features derived from audio transcriptions achieve the best performance, scoring an MAE of 4.11 (corresponding to an RMSE of 4.94), which makes our system the winner of the AVEC 2017 depression sub-challenge.

[100]  arXiv:1711.06100 [pdf, other]
Title: Sequences, Items And Latent Links: Recommendation With Consumed Item Packs
Comments: 12 pages
Subjects: Information Retrieval (cs.IR); Social and Information Networks (cs.SI); Machine Learning (stat.ML)

Recommenders personalize the web content by typically using collaborative filtering to relate users (or items) based on explicit feedback, e.g., ratings. The difficulty of collecting this feedback has recently motivated to consider implicit feedback (e.g., item consumption along with the corresponding time).
In this paper, we introduce the notion of consumed item pack (CIP) which enables to link users (or items) based on their implicit analogous consumption behavior. Our proposal is generic, and we show that it captures three novel implicit recommenders: a user-based (CIP-U), an item-based (CIP-I), and a word embedding-based (DEEPCIP), as well as a state-of-the-art technique using implicit feedback (FISM). We show that our recommenders handle incremental updates incorporating freshly consumed items. We demonstrate that all three recommenders provide a recommendation quality that is competitive with state-of-the-art ones, including one incorporating both explicit and implicit feedback.

[101]  arXiv:1711.06101 [pdf, other]
Title: Physical Layer Authentication for Mission Critical Machine Type Communication using Gaussian Mixture Model based Clustering
Comments: arXiv admin note: text overlap with arXiv:1711.03806 and substantial text overlap with arXiv:1711.05088
Subjects: Networking and Internet Architecture (cs.NI); Signal Processing (eess.SP)

The application of Mission Critical Machine Type Communication (MC-MTC) in wireless systems is currently a hot research topic. Wireless systems are considered to provide numerous advantages over wired systems in e.g. industrial applications such as closed loop control. However, due to the broadcast nature of the wireless channel, such systems are prone to a wide range of cyber attacks. These range from passive eavesdropping attacks to active attacks like data manipulation or masquerade attacks. Therefore it is necessary to provide reliable and efficient security mechanisms. Some of the most important security issues in such a system are to ensure integrity as well as authenticity of exchanged messages over the air between communicating devices. In the present work, an approach on how to achieve this goal in MC-MTC systems based on Physical Layer Security (PHYSEC) is presented. A new method that clusters channel estimates of different transmitters based on a Gaussian Mixture Model is applied for that purpose. Further, an experimental proof-of-concept evaluation is given and we compare the performance of our approach with a mean square error based detection method.

[102]  arXiv:1711.06104 [pdf, other]
Title: A unified view of gradient-based attribution methods for Deep Neural Networks
Comments: Accepted at NIPS 2017 - Workshop Interpreting, Explaining and Visualizing Deep Learning
Subjects: Learning (cs.LG); Machine Learning (stat.ML)

Understanding the flow of information in Deep Neural Networks is a challenging problem that has gain increasing attention over the last few years. While several methods have been proposed to explain network predictions, only few attempts to analyze them from a theoretical perspective have been made in the past. In this work we analyze various state-of-the-art attribution methods and prove unexplored connections between them. We also show how some methods can be reformulated and more conveniently implemented. Finally, we perform an empirical evaluation with six attribution methods on a variety of tasks and architectures and discuss their strengths and limitations.

[103]  arXiv:1711.06106 [pdf, other]
Title: Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Contemporary benchmark methods for image inpainting are based on deep generative models and specifically leverage adversarial loss for yielding realistic reconstructions. However, these models cannot be directly applied on image/video sequences because of an intrinsic drawback- the reconstructions might be independently realistic, but, when visualized as a sequence, often lacks fidelity to the original uncorrupted sequence. The fundamental reason is that these methods try to find the best matching latent space representation near to natural image manifold without any explicit distance based loss. In this paper, we present a semantically conditioned Generative Adversarial Network (GAN) for sequence inpainting. The conditional information constrains the GAN to map a latent representation to a point in image manifold respecting the underlying pose and semantics of the scene. To the best of our knowledge, this is the first work which simultaneously addresses consistency and correctness of generative model based inpainting. We show that our generative model learns to disentangle pose and appearance information; this independence is exploited by our model to generate highly consistent reconstructions. The conditional information also aids the generator network in GAN to produce sharper images compared to the original GAN formulation. This helps in achieving more appealing inpainting performance. Though generic, our algorithm was targeted for inpainting on faces. When applied on CelebA and Youtube Faces datasets, the proposed method results in a significant improvement over the current benchmark, both in terms of quantitative evaluation (Peak Signal to Noise Ratio) and human visual scoring over diversified combinations of resolutions and deformations.

[104]  arXiv:1711.06109 [pdf]
Title: Database Normalization Debt: A Debt-Aware Approach to Reason about Normalization Decisions in Database Design
Subjects: Software Engineering (cs.SE)

Technical debt is a metaphor that describes the long term effects of shortcuts taken in software development activities to achieve near term goals. In this study, we explore a new context of technical debt that relates to database normalization design decisions. We posit that ill normalized databases can have long term ramifications on data quality, performance degradation and maintainability costs over time, just like debts accumulate interest. Conversely, conventional database approaches would suggest normalizing weakly normalized tables, this can be a costly process in terms of effort and expertise it requires for large software systems. As studies have shown that the fourth normal form is often regarded as the ideal form in database design, we claim that database normalization debts are likely to be incurred for tables below this form. We refer to normalization debt item as any table in the database below the fourth normal form.
We propose a framework for identifying normalization debt. Our framework makes use of association rule mining to discover functional dependencies between attributes in a table, which will help determine the current normal form of that table and identify debt tables. To manage such debts, we propose a trade off analysis method to prioritize tables that are candidate for normalization. The trade off is between the rework cost and the debt effect on the quality of the system as the metaphoric interest. To evaluate our method, we use a case study from Microsoft, AdventureWorks. The results show that our method can reduce the cost and effort of normalization, while improving the database design.

[105]  arXiv:1711.06115 [pdf, other]
Title: An introduction to approximate computing
Subjects: Programming Languages (cs.PL)

Approximate computing is a research area where we investigate a wide spectrum of techniques to trade off accuracy of computation for better performance or energy consumption. We provide in this article a general introduction to approximate computing. Also, we propose a taxonomy to make it easier to discuss the merits of different approximation techniques. Our taxonomy emphasizes the cost expected for tackling AC across the entire system stack. We provide selected pointers to the literature based on the proposed taxonomy.

[106]  arXiv:1711.06116 [pdf, other]
Title: Personalized Driver Stress Detection with Multi-task Neural Networks using Physiological Signals
Comments: 6 pages, 1 figure, 2 tables, NIPS - Machine Learning for Health Workshop
Subjects: Human-Computer Interaction (cs.HC)

Stress can be seen as a physiological response to everyday emotional, mental and physical challenges. A long-term exposure to stressful situations can have negative health consequences, such as increased risk of cardiovascular diseases and immune system disorder. Therefore, a timely stress detection can lead to systems for better management and prevention in future circumstances. In this paper, we suggest a multi-task learning based neural network approach (with hard parameter sharing of mutual representation and task-specific layers) for personalized stress recognition using skin conductance and heart rate from wearable devices. The proposed method is tested on multi-modal physiological responses collected during real-world and simulator driving tasks.

[107]  arXiv:1711.06120 [pdf, ps, other]
Title: Game Characterization of Probabilistic Bisimilarity, and Applications to Pushdown Automata
Comments: This paper extends and strengthens a preliminary version from FSTTCS'12
Subjects: Logic in Computer Science (cs.LO); Formal Languages and Automata Theory (cs.FL)

We study the bisimilarity problem for probabilistic pushdown automata (pPDA) and subclasses thereof. Our definition of pPDA allows both probabilistic and non-deterministic branching, generalising the classical notion of pushdown automata (without epsilon-transitions). We first show a general characterization of probabilistic bisimilarity in terms of two-player games, which naturally reduces checking bisimilarity of probabilistic labelled transition systems to checking bisimilarity of standard (non-deterministic) labelled transition systems. This reduction can be easily implemented in the framework of pPDA, allowing to use known results for standard (non-probabilistic) PDA and their subclasses. A direct use of the reduction incurs an exponential increase of complexity, which does not matter in deriving decidability of bisimilarity for pPDA due to the non-elementary complexity of the problem. In the cases of probabilistic one-counter automata (pOCA), of probabilistic visibly pushdown automata (pvPDA), and of probabilistic basic process algebras (i.e., single-state pPDA) we show that an implicit use of the reduction can avoid the complexity increase; we thus get PSPACE, EXPTIME, and 2-EXPTIME upper bounds, respectively, like for the respective non-probabilistic versions. The bisimilarity problems for OCA and vPDA are known to have matching lower bounds (thus being PSPACE-complete and EXPTIME-complete, respectively); we show that these lower bounds also hold for fully probabilistic versions that do not use non-determinism.

[108]  arXiv:1711.06127 [pdf, other]
Title: SUPRA: Open Source Software Defined Ultrasound Processing for Real-Time Applications
Comments: Submitted to IPCAI 2018
Subjects: Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)

Research in ultrasound imaging is limited in reproducibility by two factors: First, many existing ultrasound pipelines are protected by intellectual property, rendering exchange of code difficult. Second, most pipelines are implemented in special hardware, resulting in limited flexibility of implemented processing steps on such platforms.
Methods: With SUPRA we propose an open-source pipeline for fully Software Defined Ultrasound Processing for Real-time Applications to alleviate these problems. Covering all steps from beamforming to output of B-mode images, SUPRA can help improve the reproducibility of results and make modifications to the image acquisition mode accessible to the research community. We evaluate the pipeline qualitatively, quantitatively, and regarding its run-time.
Results: The pipeline shows image quality comparable to a clinical system and backed by point-spread function measurements a comparable resolution. Including all processing stages of a usual ultrasound pipeline, the run-time analysis shows that it can be executed in 2D and 3D on consumer GPUs in real-time.
Conclusions: Our software ultrasound pipeline opens up the research in image acquisition. Given access to ultrasound data from early stages (raw channel data, radiofrequency data) it simplifies the development in imaging. Furthermore, it tackles the reproducibility of research results, as code can be shared easily and even be executed without dedicated ultrasound hardware.

[109]  arXiv:1711.06128 [pdf, ps, other]
Title: Enabling Reasoning with LegalRuleML
Comments: 22 pages. Under consideration for publication in Theory and Practice of Logic Programming (TPLP)
Subjects: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)

In order to automate verification process, regulatory rules written in natural language needs to be translated into a format that machines can understand. However, none of the existing formalisms can fully represent the elements that appear in legal norms. For instance, most of these formalisms do not provide features to capture the behavior of deontic effects, which is an important aspect in automated compliance checking. This paper presents an approach for transforming legal norms represented using LegalRuleML to a variant of Modal Defeasible Logic (and vice versa) such that legal statement represented using LegalRuleML can be transformed into a machine readable format that can be understand and reasoned about depending upon the client's preferences.

[110]  arXiv:1711.06134 [pdf]
Title: "Making you happy makes me happy" - Measuring Individual Mood with Smartwatches
Comments: 14 pages, 10 figures
Subjects: Human-Computer Interaction (cs.HC)

We introduce a system to measure individual happiness based on interpreting body sensors on smartwatches. In our prototype system we use a Pebble smartwatch to track activity, heartrate, light level, and GPS coordinates, and extend it with external information such as weather data, humidity, and day of the week. Training our machine learning-based mood prediction system using random forests with data manually entered into the smartwatch, we achieve prediction accuracy of up to 94%. We find that besides body signals, the weather data exerts a strong influence on mood. In addition our system also allows us to identify friends who are indicators of our positive or negative mood.

[111]  arXiv:1711.06136 [pdf, other]
Title: 3D Trajectory Reconstruction of Dynamic Objects Using Planarity Constraints
Comments: 9 Pages, under review
Subjects: Computer Vision and Pattern Recognition (cs.CV)

We present a method to reconstruct the three-dimensional trajectory of a moving instance of a known object category in monocular video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic segmentation techniques and optical flow cues. We apply Structure from Motion techniques to object and background images to determine for each frame camera poses relative to object instances and background structures. By combining object and background camera pose information, we restrict the object trajectory to a one-parameter family of possible solutions. We compute a ground representation by fusing background structures and corresponding semantic segmentations. This allows us to determine an object trajectory consistent to image observations and reconstructed environment model. Our method is robust to occlusion and handles temporarily stationary objects. We show qualitative results using drone imagery. Due to the lack of suitable benchmark datasets we present a new dataset to evaluate the quality of reconstructed three-dimensional object trajectories. The video sequences contain vehicles in urban areas and are rendered using the path-tracing render engine Cycles to achieve realistic results. We perform a quantitative evaluation of the presented approach using this dataset. Our algorithm achieves an average reconstruction-to-ground-truth distance of 0.31 meter.

[112]  arXiv:1711.06141 [pdf, other]
Title: ConvAMR: Abstract meaning representation parsing
Comments: SCIDOCA2017, Japan
Subjects: Computation and Language (cs.CL)

Convolutional neural networks (CNN) have recently achieved remarkable performance in a wide range of applications. In this research, we equip convolutional sequence-to-sequence (seq2seq) model with an efficient graph linearization technique for abstract meaning representation parsing. Our linearization method is better than the prior method at signaling the turn of graph traveling. Additionally, convolutional seq2seq model is more appropriate and considerably faster than the recurrent neural network models in this task. Our method outperforms previous methods by a large margin on both the standard dataset LDC2014T12. Our result indicates that future works still have a room for improving parsing model using graph linearization approach.

[113]  arXiv:1711.06148 [pdf, other]
Title: Learning Compositional Visual Concepts with Mutual Consistency
Comments: 10 pages, 7 figures, 4 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Compositionality of semantic concepts in image synthesis and analysis is appealing as it can help in decomposing known and generatively recomposing unknown data. For instance, we may learn concepts of changing illumination, geometry or albedo of a scene, and try to recombine them to generate physically meaningful, but unseen data for training and testing. In practice however we often do not have samples from the joint concept space available: We may have data on illumination change in one data set and on geometric change in another one without complete overlap. We pose the following question: How can we learn two or more concepts jointly from different data sets with mutual consistency where we do not have samples from the full joint space? We present a novel answer in this paper based on cyclic consistency over multiple concepts, represented individually by generative adversarial networks (GANs). Our method, ConceptGAN, can be understood as a drop in for data augmentation to improve resilience for real world applications. Qualitative and quantitative evaluations demonstrate its efficacy in generating semantically meaningful images, as well as one shot face verification as an example application.

[114]  arXiv:1711.06149 [pdf, other]
Title: MindID: Person Identification from Brain Waves through Attention-based Recurrent Neural Network
Comments: 20 pages
Subjects: Human-Computer Interaction (cs.HC)

Person identification technology recognizes individuals by exploiting their unique, measurable physiological and behavioral characteristics. However, the state-of-the-art person identification systems have been shown to be vulnerable, e.g., contact lenses can trick iris recognition and fingerprint films can deceive fingerprint sensors. EEG (Electroencephalography)-based identification, which utilizes the users brainwave signals for identification and offers a more resilient solution, draw a lot of attention recently. However, the accuracy still requires improvement and very little work is focusing on the robustness and adaptability of the identification system. We propose MindID, an EEG-based biometric identification approach, achieves higher accuracy and better characteristics. At first, the EEG data patterns are analyzed and the results show that the Delta pattern contains the most distinctive information for user identification. Then the decomposed Delta pattern is fed into an attention-based Encoder-Decoder RNNs (Recurrent Neural Networks) structure which assigns varies attention weights to different EEG channels based on the channels importance. The discriminative representations learned from the attention-based RNN are used to recognize the user identification through a boosting classifier. The proposed approach is evaluated over 3 datasets (two local and one public). One local dataset (EID-M) is used for performance assessment and the result illustrate that our model achieves the accuracy of 0.982 which outperforms the baselines and the state-of-the-art. Another local dataset (EID-S) and a public dataset (EEG-S) are utilized to demonstrate the robustness and adaptability, respectively. The results indicate that the proposed approach has the potential to be largely deployment in practice environment.

[115]  arXiv:1711.06154 [pdf, other]
Title: Reliable Video Streaming over mmWave with Multi Connectivity and Network Coding
Comments: To be presented at the 2017 IEEE International Conference on Computing, Networking and Communications (ICNC), March 2017, Maui, Hawaii, USA (invited paper). 6 pages, 4 figures
Subjects: Networking and Internet Architecture (cs.NI); Information Theory (cs.IT)

The next generation of multimedia applications will require the telecommunication networks to support a higher bitrate than today, in order to deliver virtual reality and ultra-high quality video content to the users. Most of the video content will be accessed from mobile devices, prompting the provision of very high data rates by next generation (5G) cellular networks. A possible enabler in this regard is communication at mmWave frequencies, given the vast amount of available spectrum that can be allocated to mobile users; however, the harsh propagation environment at such high frequencies makes it hard to provide a reliable service. This paper presents a reliable video streaming architecture for mmWave networks, based on multi connectivity and network coding, and evaluates its performance using a novel combination of the ns-3 mmWave module, real video traces and the network coding library Kodo. The results show that it is indeed possible to reliably stream video over cellular mmWave links, while the combination of multi connectivity and network coding can support high video quality with low latency.

[116]  arXiv:1711.06162 [pdf, ps, other]
Title: Joint Power Control and Beamforming for Uplink Non-Orthogonal Multiple Access in 5G Millimeter-Wave Communications
Comments: 12 pages, 9 figures. arXiv admin note: substantial text overlap with arXiv:1711.01380
Subjects: Information Theory (cs.IT)

In this paper, we investigate the combination of two key enabling technologies for the fifth generation (5G) wireless mobile communication, namely millimeter-wave (mmWave) communications and non-orthogonal multiple access (NOMA). In particular, we consider a typical 2-user uplink mmWave-NOMA system, where the base station (BS) equips an analog beamforming structure with a single RF chain and serves 2 NOMA users. An optimization problem is formulated to maximize the achievable sum rate of the 2 users while ensuring a minimal rate constraint for each user. The problem turns to be a joint power control and beamforming problem, i.e., we need to find the beamforming vectors to steer to the two users simultaneously subject to an analog beamforming structure, and meanwhile control appropriate power on them. As direct search for the optimal solution of the non-convex problem is too complicated, we propose to decompose the original problem into two sub-problems that are relatively easy to solve: one is a power control and beam gain allocation problem, and the other is an analog beamforming problem under a constant-modulus constraint. The rational of the proposed solution is verified by extensive simulations, and the performance evaluation results show that the proposed sub-optimal solution achieve a close-to-bound uplink sum-rate performance.

[117]  arXiv:1711.06167 [pdf, ps, other]
Title: Zero-Shot Learning via Category-Specific Visual-Semantic Mapping
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Zero-Shot Learning (ZSL) aims to classify a test instance from an unseen category based on the training instances from seen categories, in which the gap between seen categories and unseen categories is generally bridged via visual-semantic mapping between the low-level visual feature space and the intermediate semantic space. However, the visual-semantic mapping learnt based on seen categories may not generalize well to unseen categories because the data distributions between seen categories and unseen categories are considerably different, which is known as the projection domain shift problem in ZSL. To address this domain shift issue, we propose a method named Adaptive Embedding ZSL (AEZSL) to learn an adaptive visual-semantic mapping for each unseen category based on the similarities between each unseen category and all the seen categories. Then, we further make two extensions based on our AEZSL method. Firstly, in order to utilize the unlabeled test instances from unseen categories, we extend our AEZSL to a semi-supervised approach named AEZSL with Label Refinement (AEZSL_LR), in which a progressive approach is developed to update the visual classifiers and refine the predicted test labels alternatively based on the similarities among test instances and among unseen categories. Secondly, to avoid learning visual-semantic mapping for each unseen category in the large-scale classification task, we extend our AEZSL to a deep adaptive embedding model named Deep AEZSL (DAEZSL) sharing the similar idea (i.e., visual-semantic mapping should be category-specific and related to the semantic space) with AEZSL, which only needs to be trained once, but can be applied to arbitrary number of unseen categories. Extensive experiments demonstrate that our proposed methods achieve the state-of-the-art results for image classification on four benchmark datasets.

[118]  arXiv:1711.06196 [pdf, other]
Title: Addressing Cross-Lingual Word Sense Disambiguation on Low-Density Languages: Application to Persian
Subjects: Computation and Language (cs.CL); Information Retrieval (cs.IR)

We explore the use of unsupervised methods in Cross-Lingual Word Sense Disambiguation (CL-WSD) with the application of English to Persian. Our proposed approach targets the languages with scarce resources (low-density) by exploiting word embedding and semantic similarity of the words in context. We evaluate the approach on a recent evaluation benchmark and compare it with the state-of-the-art unsupervised system (CO-Graph). The results show that our approach outperforms both the standard baseline and the CO-Graph system in both of the task evaluation metrics (Out-Of-Five and Best result).

[119]  arXiv:1711.06202 [pdf, ps, other]
Title: A Robust Genetic Algorithm for Learning Temporal Specifications from Data
Comments: 6 pages, 1 figure
Subjects: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)

We consider the problem of mining signal temporal logical requirements from a dataset of regular (good) and anomalous (bad) trajectories of a dynamical system. We assume the training set to be labeled by human experts and that we have access only to a limited amount of data, typically noisy. We provide a systematic approach to synthesize both the syntactical structure and the parameters of the temporal logic formula using a two-steps procedure: first, we leverage a novel evolutionary algorithm for learning the structure of the formula, second, we perform the parameter synthesis operating on the statistical emulation of the average robustness for a candidate formula w.r.t. its parameters. We test our algorithm on a anomalous trajectory detection problem of a naval surveillance system and we compare our results with our previous work~\cite{BufoBSBLB14} and with a recently proposed decision-tree~\cite{bombara_decision_2016} based method. Our experiments indicate that the proposed approach outperforms our previous work w.r.t. accuracy and show that it produces in general smaller and more compact temporal logic specifications w.r.t. the decision-tree based approach with a comparable speed and accuracy.

[120]  arXiv:1711.06232 [pdf, other]
Title: A Novel Framework for Robustness Analysis of Visual QA Models
Comments: Submitted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Subjects: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)

Deep neural networks have been playing an essential role in many computer vision tasks including Visual Question Answering (VQA). Until recently, the study of their accuracy has been the main focus of research and now there is a huge trend toward assessing the robustness of these models against adversarial attacks by evaluating the accuracy of these models under increasing levels of noisiness. In VQA, the attack can target the image and/or the proposed main question and yet there is a lack of proper analysis of this aspect of VQA. In this work, we propose a new framework that uses semantically relevant questions, dubbed basic questions, acting as noise to evaluate the robustness of VQA models. We hypothesize that as the similarity of a basic question to the main question decreases, the level of noise increases. So, to generate a reasonable noise level for a given main question, we rank a pool of basic questions based on their similarity with this main question. We cast this ranking problem as a LASSO optimization problem. We also propose a novel robustness measure R_score and two large-scale question datasets, General Basic Question Dataset and Yes/No Basic Question Dataset in order to standardize robustness analysis of VQA models. We analyze the robustness of several state-of-the-art VQA models and show that attention-based VQA models are more robust than other methods in general. The main goal of this framework is to serve as a benchmark to help the community in building more accurate and robust VQA models.

[121]  arXiv:1711.06234 [pdf, other]
Title: Privacy-preserving Edit Distance on Genomic Data
Comments: 5 pages, 1 figure, 2 algorithm
Subjects: Cryptography and Security (cs.CR)

Suppose Alice holds a DNA sequence and Bob owns a database of DNA sequences. They want to determine whether there is a match for the Alice's input in the Bob's database for any purpose such as diagnosis of Alice's disease. However, Alice does not want to reveal her DNA pattern to Bob, since it would enable him to learn private information about her. For the similar reasons, Bob does not want to reveal any information about his database to Alice. This problem has attracted attention from bioinformatics community in order to protect privacy of users and several solutions have been proposed. Efficiency is always a bottleneck in cryptography domain. In this paper, we propose ESCOT protocol to address privacy preserving Edit distance using Oblivious Transfer (OT) for the first time. We evaluate our approach on a genome dataset over both LAN and WAN network. Experimental results confirm feasibility of our approach in real-world scenarios.

[122]  arXiv:1711.06238 [pdf, other]
Title: An Abstractive approach to Question Answering
Authors: Rajarshee Mitra
Subjects: Computation and Language (cs.CL)

Question Answering has come a long way from answer sentence selection, relational QA to reading and comprehension. We move our attention to abstractive question answering by which we facilitate machine to read passages and answer questions by generating them. We frame the problem as a sequence to sequence learning where the encoder being a network that models the relation between question and passage, thereby relying solely on passage and question content to form an abstraction of the answer. Not being able to retain facts and making repetitions are common mistakes that affect the overall legibility of answers. To counter these issues, we employ copying mechanism and maintenance of coverage vector in our model respectively. Our results on MS-MARCO demonstrates it's superiority over baselines and we also show qualitative examples where we improved in terms of correctness and readability.

[123]  arXiv:1711.06241 [pdf, other]
Title: Deceptiveness of internet data for disease surveillance
Comments: 26 pages, 6 figures
Subjects: Information Theory (cs.IT); Social and Information Networks (cs.SI); Populations and Evolution (q-bio.PE); Applications (stat.AP)

Quantifying how many people are or will be sick, and where, is a critical ingredient in reducing the burden of disease because it helps the public health system plan and implement effective outbreak response. This process of disease surveillance is currently based on data gathering using clinical and laboratory methods; this distributed human contact and resulting bureaucratic data aggregation yield expensive procedures that lag real time by weeks or months. The promise of new surveillance approaches using internet data, such as web event logs or social media messages, is to achieve the same goal but faster and cheaper. However, prior work in this area lacks a rigorous model of information flow, making it difficult to assess the reliability of both specific approaches and the body of work as a whole.
We model disease surveillance as a Shannon communication. This new framework lets any two disease surveillance approaches be compared using a unified vocabulary and conceptual model. Using it, we describe and compare the deficiencies suffered by traditional and internet-based surveillance, introduce a new risk metric called deceptiveness, and offer mitigations for some of these deficiencies. This framework also makes the rich tools of information theory applicable to disease surveillance. This better understanding will improve the decision-making of public health practitioners by helping to leverage internet-based surveillance in a way complementary to the strengths of traditional surveillance.

[124]  arXiv:1711.06246 [pdf, other]
Title: LDMNet: Low Dimensional Manifold Regularized Neural Networks
Subjects: Computer Vision and Pattern Recognition (cs.CV)

Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers from overfitting. Many existing methods of reducing overfitting are data-independent, and their efficacy is often limited when the training set is very small. Data-dependent regularizations are mostly motivated by the observation that data of interest lie close to a manifold, which is typically hard to parametrize explicitly and often requires human input of tangent vectors. These methods typically only focus on the geometry of the input data, and do not necessarily encourage the networks to produce geometrically meaningful features. To resolve this, we propose a new framework, the Low-Dimensional-Manifold-regularized neural Network (LDMNet), which incorporates a feature regularization method that focuses on the geometry of both the input data and the output features. In LDMNet, we regularize the network by encouraging the combination of the input data and the output features to sample a collection of low dimensional manifolds, which are searched efficiently without explicit parametrization. To achieve this, we directly use the manifold dimension as a regularization term in a variational functional. The resulting Euler-Lagrange equation is a Laplace-Beltrami equation over a point cloud, which is solved by the point integral method without increasing the computational complexity. We demonstrate two benefits of LDMNet in the experiments. First, we show that LDMNet significantly outperforms widely-used network regularizers such as weight decay and DropOut. Second, we show that LDMNet can be designed to extract common features of an object imaged via different modalities, which proves to be very useful in real-world applications such as cross-spectral face recognition.

Cross-lists for Fri, 17 Nov 17

[125]  arXiv:1711.05762 (cross-list from math.OC) [pdf, other]
Title: Random gradient extrapolation for distributed and stochastic optimization
Authors: Guanghui Lan, Yi Zhou
Subjects: Optimization and Control (math.OC); Computational Complexity (cs.CC); Learning (cs.LG); Machine Learning (stat.ML)

In this paper, we consider a class of finite-sum convex optimization problems defined over a distributed multiagent network with $m$ agents connected to a central server. In particular, the objective function consists of the average of $m$ ($\ge 1$) smooth components associated with each network agent together with a strongly convex term. Our major contribution is to develop a new randomized incremental gradient algorithm, namely random gradient extrapolation method (RGEM), which does not require any exact gradient evaluation even for the initial point, but can achieve the optimal ${\cal O}(\log(1/\epsilon))$ complexity bound in terms of the total number of gradient evaluations of component functions to solve the finite-sum problems. Furthermore, we demonstrate that for stochastic finite-sum optimization problems, RGEM maintains the optimal ${\cal O}(1/\epsilon)$ complexity (up to a certain logarithmic factor) in terms of the number of stochastic gradient computations, but attains an ${\cal O}(\log(1/\epsilon))$ complexity in terms of communication rounds (each round involves only one agent). It is worth noting that the former bound is independent of the number of agents $m$, while the latter one only linearly depends on $m$ or even $\sqrt m$ for ill-conditioned problems. To the best of our knowledge, this is the first time that these complexity bounds have been obtained for distributed and stochastic optimization problems. Moreover, our algorithms were developed based on a novel dual perspective of Nesterov's accelerated gradient method.

[126]  arXiv:1711.05807 (cross-list from math.NT) [pdf, ps, other]
Title: Set complexity of construction of a regular polygon
Authors: Eugene Kogan
Comments: 4 pages, in Russian
Subjects: Number Theory (math.NT); Computational Complexity (cs.CC)

Given a subset of $\mathbb C$ containing $x,y$, one can add $x + y$ or $x - y$ or $xy$ or (when $y\ne0$) $x/y$ or any $z$ such that $z^2=x$. Let $p$ be a prime Fermat number. We prove that it is possible to obtain from $\{1\}$ a set containing all the $p$-th roots of 1 by $16 p^2$ above operations. This problem is different from the standard estimation of complexity of an algorithm computing the $p$-th roots of 1.

[127]  arXiv:1711.05812 (cross-list from math.OC) [pdf, ps, other]
Title: Global convergence rates of augmented Lagrangian methods for constrained convex programming
Authors: Yangyang Xu
Subjects: Optimization and Control (math.OC); Data Structures and Algorithms (cs.DS); Numerical Analysis (math.NA)

Augmented Lagrangian method (ALM) has been popularly used for solving constrained optimization problems. Its convergence and local convergence speed have been extensively studied. However, its global convergence rate is still open for problems with nonlinear inequality constraints. In this paper, we work on general constrained convex programs. For these problems, we establish the global convergence rate of ALM and its inexact variants.
We first assume exact solution to each subproblem in the ALM framework and establish an $O(1/k)$ ergodic convergence result, where $k$ is the number of iterations. Then we analyze an inexact ALM that approximately solves the subproblems. Assuming summable errors, we prove that the inexact ALM also enjoys $O(1/k)$ convergence if smaller stepsizes are used in the multiplier updates. Furthermore, we apply the inexact ALM to a constrained composite convex problem with each subproblem solved by Nesterov's optimal first-order method. We show that $O(\varepsilon^{-\frac{3}{2}-\delta})$ gradient evaluations are sufficient to guarantee an $\varepsilon$-optimal solution in terms of both primal objective and feasibility violation, where $\delta$ is an arbitrary positive number. Finally, for constrained smooth problems, we modify the inexact ALM by adding a proximal term to each subproblem and improve the iteration complexity to $O(\varepsilon^{-1}|\log\varepsilon|)$.

[128]  arXiv:1711.05814 (cross-list from math.GR) [pdf, ps, other]
Title: Python Implementation and Construction of Finite Abelian Groups
Comments: 20 pages
Subjects: Group Theory (math.GR); Mathematical Software (cs.MS)

Here we present a working framework to establish finite abelian groups in python. The primary aim is to allow new A-level students to work with examples of finite abelian groups using open source software. We include the code used in the implementation of the framework. We also prove some useful results regarding finite abelian groups which are used to establish the functions and help show how number theoretic results can blend with computational power when studying algebra. The groups established are based modular multiplication and addition. We include direct products of cyclic groups meaning the user has access to all finite abelian groups.

[129]  arXiv:1711.05825 (cross-list from stat.CO) [pdf, other]
Title: Bootstrapped synthetic likelihood
Subjects: Computation (stat.CO); Artificial Intelligence (cs.AI); Data Analysis, Statistics and Probability (physics.data-an); Methodology (stat.ME); Machine Learning (stat.ML)

The development of approximate Bayesian computation (ABC) and synthetic likelihood (SL) techniques has enabled the use of Bayesian inference for models that may be simulated, but for which the likelihood is not available to evaluate pointwise at values of an unknown parameter $\theta$. The main idea in ABC and SL is to, for different values of $\theta$ (usually chosen using a Monte Carlo algorithm), build estimates of the likelihood based on simulations from the model conditional on $\theta$. The quality of these estimates determines the efficiency of an ABC/SL algorithm. In standard ABC/SL, the only means to improve an estimated likelihood at $\theta$ is to simulate more times from the model conditional on $\theta$, which is infeasible in cases where the simulator is computationally expensive. In this paper we describe how to use bootstrapping as a means for improving synthetic likelihood estimates whilst using fewer simulations from the model, and also investigate its use in ABC. Further, we investigate the use of the bag of little bootstraps as a means for applying this approach to large datasets, yielding to Monte Carlo algorithms that accurately approximate posterior distributions whilst only simulating subsamples of the full data. Examples of the approach applied to i.i.d., temporal and spatial data are given.

[130]  arXiv:1711.05837 (cross-list from eess.SP) [pdf, ps, other]
Title: Crowd Counting Through Walls Using WiFi
Comments: 10 pages, 14 figures
Subjects: Signal Processing (eess.SP); Networking and Internet Architecture (cs.NI)

Counting the number of people inside a building, from outside and without entering the building, is crucial for many applications. In this paper, we are interested in counting the total number of people walking inside a building (or in general behind walls), using readily-deployable WiFi transceivers that are installed outside the building, and only based on WiFi RSSI measurements. The key observation of the paper is that the inter-event times, corresponding to the dip events of the received signal, are fairly robust to the attenuation through walls (for instance as compared to the exact dip values). We then propose a methodology that can extract the total number of people from the inter-event times. More specifically, we first show how to characterize the wireless received power measurements as a superposition of renewal-type processes. By borrowing theories from the renewal-process literature, we then show how the probability mass function of the inter-event times carries vital information on the number of people. We validate our framework with 44 experiments in five different areas on our campus (3 classrooms, a conference room, and a hallway), using only one WiFi transmitter and receiver installed outside of the building, and for up to and including 20 people. Our experiments further include areas with different wall materials, such as concrete, plaster, and wood, to validate the robustness of the proposed approach. Overall, our results show that our approach can estimate the total number of people behind the walls with a high accuracy while minimizing the need for prior calibrations.

[131]  arXiv:1711.05855 (cross-list from eess.SP) [pdf, ps, other]
Title: Passive Crowd Speed Estimation With WiFi
Comments: 13 pages, 13 figures
Subjects: Signal Processing (eess.SP); Networking and Internet Architecture (cs.NI)

In this paper, we propose a methodology for estimating the crowd speed using WiFi devices, and without relying on people to carry any device (passively). Our approach not only enables speed estimation in the region where WiFi links are, but also in the adjacent possibly WiFi-free regions where there may be no WiFi signal available. More specifically, we use a pair of WiFi links in one region, whose RSSI measurements are then used to estimate the crowd speed, not only in this region, but also in adjacent WiFi-free regions. We first prove how the cross-correlation and the probability of crossing of the two links implicitly carry key information about the pedestrian speeds and develop a mathematical model to relate them to pedestrian speeds. We then validate our approach with 108 experiments, in both indoor and outdoor, where up to 10 people walk in two adjacent areas, with a variety of speeds per region, showing that our framework can accurately estimate these speeds with only a pair of WiFi links in one region. For instance, the NMSE over all experiments is 0.18. Furthermore, the overall classification accuracy, when crowd speed is categorized as slow, normal, and fast, is 85%. We also evaluate our framework in a museum-type setting, where two exhibitions showcase two different types of displays. We show how our methodology can estimate the visitor speeds in both exhibits, deducing which exhibit is more popular. We finally run experiments in an aisle in Costco, estimating key attributes of buyers' behaviors.

[132]  arXiv:1711.05866 (cross-list from physics.comp-ph) [pdf, other]
Title: Fast and Efficient Calculations of Structural Invariants of Chirality
Subjects: Computational Physics (physics.comp-ph); Computer Vision and Pattern Recognition (cs.CV)

Chirality plays an important role in physics, chemistry, biology, and other fields. It describes an essential symmetry in structure. However, chirality invariants are usually complicated in expression or difficult to evaluate. In this paper, we present five general three-dimensional chirality invariants based on the generating functions which are called ShapeDNA. And the five chiral invariants have three characteristics: 1) Three of the five chiral invariants decode the universal chirality index G0 in specified circumstance. 2) Three of them are proposed for the first time. 3) The five chiral invariants have low order no bigger than 4, brief expression, low time complexity O(n) and can act as descriptors of three-dimensional objects in shape analysis. The five chiral invariants give a geometric view to study the chiral invariants. And the experiments show that the five chirality invariants are effective and efficient, they can be used as a tool for symmetry detection or features in shape analysis.

[133]  arXiv:1711.05869 (cross-list from stat.ML) [pdf, other]
Title: Predictive Independence Testing, Predictive Conditional Independence Testing, and Predictive Graphical Modelling
Subjects: Machine Learning (stat.ML); Learning (cs.LG); Statistics Theory (math.ST); Methodology (stat.ME)

Testing (conditional) independence of multivariate random variables is a task central to statistical inference and modelling in general - though unfortunately one for which to date there does not exist a practicable workflow. State-of-art workflows suffer from the need for heuristic or subjective manual choices, high computational complexity, or strong parametric assumptions.
We address these problems by establishing a theoretical link between multivariate/conditional independence testing, and model comparison in the multivariate predictive modelling aka supervised learning task. This link allows advances in the extensively studied supervised learning workflow to be directly transferred to independence testing workflows - including automated tuning of machine learning type which addresses the need for a heuristic choice, the ability to quantitatively trade-off computational demand with accuracy, and the modern black-box philosophy for checking and interfacing.
As a practical implementation of this link between the two workflows, we present a python package 'pcit', which implements our novel multivariate and conditional independence tests, interfacing the supervised learning API of the scikit-learn package. Theory and package also allow for straightforward independence test based learning of graphical model structure.
We empirically show that our proposed predictive independence test outperform or are on par to current practice, and the derived graphical model structure learning algorithms asymptotically recover the 'true' graph. This paper, and the 'pcit' package accompanying it, thus provide powerful, scalable, generalizable, and easy-to-use methods for multivariate and conditional independence testing, as well as for graphical model structure learning.

[134]  arXiv:1711.05877 (cross-list from math.CO) [pdf, ps, other]
Title: Packing nearly optimal Ramsey R(3,t) graphs
Authors: He Guo, Lutz Warnke
Comments: 22 pages
Subjects: Combinatorics (math.CO); Discrete Mathematics (cs.DM); Probability (math.PR)

In 1995 Kim famously proved the Ramsey bound R(3,t) \ge c t^2/\log t by constructing an n-vertex graph that is triangle-free and has independence number at most C \sqrt{n \log n}. We extend this celebrated result, which is best possible up to the value of the constants, by approximately decomposing the complete graph K_n into a packing of such nearly optimal Ramsey R(3,t) graphs.
More precisely, for any \epsilon>0 we find an edge-disjoint collection (G_i)_i of n-vertex graphs G_i \subseteq K_n such that (a) each G_i is triangle-free and has independence number at most C_\epsilon \sqrt{n \log n}, and (b) the union of all the G_i contains at least (1-\epsilon)\binom{n}{2} edges. Our algorithmic proof proceeds by sequentially choosing the graphs G_i via a semi-random (i.e., Rodl nibble type) variation of the triangle-free process.
As an application, we prove a conjecture in Ramsey theory by Fox, Grinshpun, Liebenau, Person, and Szabo (concerning a Ramsey-type parameter introduced by Burr, Erdos, Lovasz in 1976). Namely, denoting by s_r(H) the smallest minimum degree of r-Ramsey minimal graphs for H, we close the existing logarithmic gap for H=K_3 and establish that s_r(K_3) = \Theta(r^2 \log r).

[135]  arXiv:1711.06064 (cross-list from stat.ML) [pdf, other]
Title: Gaussian Process Decentralized Data Fusion Meets Transfer Learning in Large-Scale Distributed Cooperative Perception
Comments: 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), Extended version with proofs, 14 pages
Subjects: Machine Learning (stat.ML); Learning (cs.LG); Multiagent Systems (cs.MA); Robotics (cs.RO)

This paper presents novel Gaussian process decentralized data fusion algorithms exploiting the notion of agent-centric support sets for distributed cooperative perception of large-scale environmental phenomena. To overcome the limitations of scale in existing works, our proposed algorithms allow every mobile sensing agent to choose a different support set and dynamically switch to another during execution for encapsulating its own data into a local summary that, perhaps surprisingly, can still be assimilated with the other agents' local summaries (i.e., based on their current choices of support sets) into a globally consistent summary to be used for predicting the phenomenon. To achieve this, we propose a novel transfer learning mechanism for a team of agents capable of sharing and transferring information encapsulated in a summary based on a support set to that utilizing a different support set with some loss that can be theoretically bounded and analyzed. To alleviate the issue of information loss accumulating over multiple instances of transfer learning, we propose a new information sharing mechanism to be incorporated into our algorithms in order to achieve memory-efficient lazy transfer learning. Empirical evaluation on real-world datasets show that our algorithms outperform the state-of-the-art methods.

[136]  arXiv:1711.06114 (cross-list from stat.ML) [pdf, other]
Title: Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
Subjects: Machine Learning (stat.ML); Learning (cs.LG)

A novel approach for unsupervised domain adaptation for neural networks is proposed that relies on a metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations by means of maximizing the similarity between domain-specific activation distributions. The proposed metric results from modifying an integral probability metric in a way such that it becomes translation-invariant on a polynomial reproducing kernel Hilbert space. The metric has an intuitive interpretation in the dual space as sum of differences of central moments of the corresponding activation distributions. As demonstrated by an analysis on standard benchmark datasets for sentiment analysis and object recognition the outlined approach shows more robustness \wrt parameter changes than state-of-the-art approaches while achieving even higher classification accuracies.

[137]  arXiv:1711.06178 (cross-list from stat.ML) [pdf, other]
Title: Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
Comments: To appear in AAAI 2018. Contains 9-page main paper and appendix with supplementary material
Subjects: Machine Learning (stat.ML); Learning (cs.LG)

The lack of interpretability remains a key barrier to the adoption of deep models in many applications. In this work, we explicitly regularize deep models so human users might step through the process behind their predictions in little time. Specifically, we train deep time-series models so their class-probability predictions have high accuracy while being closely modeled by decision trees with few nodes. Using intuitive toy examples as well as medical tasks for treating sepsis and HIV, we demonstrate that this new tree regularization yields models that are easier for humans to simulate than simpler L1 or L2 penalties without sacrificing predictive power.

[138]  arXiv:1711.06195 (cross-list from stat.ML) [pdf, other]
Title: Neurology-as-a-Service for the Developing World
Comments: Presented at NIPS 2017 Workshop on Machine Learning for the Developing World
Subjects: Machine Learning (stat.ML); Learning (cs.LG)

Electroencephalography (EEG) is an extensively-used and well-studied technique in the field of medical diagnostics and treatment for brain disorders, including epilepsy, migraines, and tumors. The analysis and interpretation of EEGs require physicians to have specialized training, which is not common even among most doctors in the developed world, let alone the developing world where physician shortages plague society. This problem can be addressed by teleEEG that uses remote EEG analysis by experts or by local computer processing of EEGs. However, both of these options are prohibitively expensive and the second option requires abundant computing resources and infrastructure, which is another concern in developing countries where there are resource constraints on capital and computing infrastructure. In this work, we present a cloud-based deep neural network approach to provide decision support for non-specialist physicians in EEG analysis and interpretation. Named `neurology-as-a-service,' the approach requires almost no manual intervention in feature engineering and in the selection of an optimal architecture and hyperparameters of the neural network. In this study, we deploy a pipeline that includes moving EEG data to the cloud and getting optimal models for various classification tasks. Our initial prototype has been tested only in developed world environments to-date, but our intention is to test it in developing world environments in future work. We demonstrate the performance of our proposed approach using the BCI2000 EEG MMI dataset, on which our service attains 63.4\% accuracy for the task of classifying real vs.\ imaginary activity performed by the subject, which is significantly higher than what is obtained with a shallow approach such as support vector machines.

[139]  arXiv:1711.06221 (cross-list from stat.ML) [pdf, other]
Title: A Forward-Backward Approach for Visualizing Information Flow in Deep Networks
Comments: Presented at NIPS 2017 Symposium on Interpretable Machine Learning
Subjects: Machine Learning (stat.ML); Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG)

We introduce a new, systematic framework for visualizing information flow in deep networks. Specifically, given any trained deep convolutional network model and a given test image, our method produces a compact support in the image domain that corresponds to a (high-resolution) feature that contributes to the given explanation. Our method is both computationally efficient as well as numerically robust. We present several preliminary numerical results that support the benefits of our framework over existing methods.

[140]  arXiv:1711.06231 (cross-list from q-bio.PE) [pdf]
Title: Extending species-area relationships (SAR) to diversity-area relationships (DAR)
Authors: Zhanshan Ma
Subjects: Populations and Evolution (q-bio.PE); Computational Engineering, Finance, and Science (cs.CE); Genomics (q-bio.GN)

I extend the traditional SAR, which has achieved status of ecological law and plays a critical role in global biodiversity assessment, to the general (alpha- or beta-diversity in Hill numbers) diversity area relationship (DAR). The extension was motivated to remedy the limitation of traditional SAR that only address one aspect of biodiversity scaling, i.e., species richness scaling over space. The extension was made possible by the fact that all Hill numbers are in units of species (referred to as the effective number of species or as species equivalents), and I postulated that Hill numbers should follow the same or similar pattern of SAR. I selected three DAR models, the traditional power law (PL), PLEC (PL with exponential cutoff) and PLIEC (PL with inverse exponential cutoff). I defined three new concepts and derived their quantifications: (i)DAR profile: z-q series where z is the PL scaling parameter at different diversity order (q); (ii)PDO (pair-wise diversity overlap) profile: g-q series where g is the PDO corresponding to q; (iii) MAD (maximal accrual diversity) profile: Dmax-q series where Dmax is the MAD corresponding to q. Furthermore, the PDO-g is quantified based on the self-similarity property of the PL model, and Dmax can be estimated from the PLEC parameters. The three profiles constitute a novel DAR approach to biodiversity scaling. I verified the postulation with the American gut microbiome project (AGP) dataset of 1473 healthy North American individuals (the largest human dataset from a single project to date). The PL model was preferred due to its simplicity and established ecological properties such as self-similarity (necessary for establishing PDO profile), and PLEC has an advantage in establishing the MAD profile. All three profiles for the AGP dataset were successfully quantified and compared with existing SAR parameters in the literature whenever possible.

[141]  arXiv:1711.06252 (cross-list from stat.ME) [pdf, other]
Title: A New Method for Performance Analysis in Nonlinear Dimensionality Reduction
Comments: 20 pages, 8 figures, 2 tables
Subjects: Methodology (stat.ME); Learning (cs.LG)

In this paper, we develop a local rank correlation measure which quantifies the performance of dimension reduction methods. The local rank correlation is easily interpretable, and robust against the extreme skewness of nearest neighbor distributions in high dimensions. Some benchmark datasets are studied. We find that the local rank correlation closely corresponds to our visual interpretation of the quality of the output. In addition, we demonstrate that the local rank correlation is useful in estimating the intrinsic dimensionality of the original data, and in selecting a suitable value of tuning parameters used in some algorithms.

Replacements for Fri, 17 Nov 17

[142]  arXiv:1307.4164 (replaced) [pdf, ps, other]
Title: Approximating Minimum Cost Connectivity Orientation and Augmentation
Subjects: Data Structures and Algorithms (cs.DS); Discrete Mathematics (cs.DM); Combinatorics (math.CO)
[143]  arXiv:1410.1042 (replaced) [pdf, ps, other]
Title: A Characterization for Decidable Separability by Piecewise Testable Languages
Subjects: Formal Languages and Automata Theory (cs.FL)
[144]  arXiv:1507.06616 (replaced) [pdf, ps, other]
Title: Robust Monotone Submodular Function Maximization
Comments: Preliminary version in IPCO 2016
Subjects: Data Structures and Algorithms (cs.DS); Discrete Mathematics (cs.DM); Optimization and Control (math.OC)
[145]  arXiv:1508.05766 (replaced) [pdf, ps, other]
Title: $n$-permutability and linear Datalog implies symmetric Datalog
Authors: Alexandr Kazda
Comments: reformated in LMCS style, 24 pages, 6 figures
Subjects: Computational Complexity (cs.CC)
[146]  arXiv:1508.07964 (replaced) [pdf, other]
Title: Wald-Kernel: Learning to Aggregate Information for Sequential Inference
Subjects: Machine Learning (stat.ML); Learning (cs.LG)
[147]  arXiv:1509.07702 (replaced) [pdf, ps, other]
Title: Fixed points and connections between positive and negative cycles in Boolean networks
Authors: Adrien Richard
Comments: 15 pages, 2 figures
Subjects: Discrete Mathematics (cs.DM)
[148]  arXiv:1602.00878 (replaced) [pdf, ps, other]
Title: On Properties of the Support of Capacity-Achieving Distributions for Additive Noise Channel Models with Input Cost Constraints
Comments: Accepted for publication in the IEEE Transactions on Information Theory with minor modifications on the current version
Subjects: Information Theory (cs.IT)
[149]  arXiv:1602.05819 (replaced) [pdf, ps, other]
Title: Constraint satisfaction problems for reducts of homogeneous graphs
Comments: 41 pages
Subjects: Logic in Computer Science (cs.LO); Computational Complexity (cs.CC); Logic (math.LO)
[150]  arXiv:1603.03833 (replaced) [pdf, other]
Title: From virtual demonstration to real-world manipulation using LSTM and MDN
Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI); Learning (cs.LG)
[151]  arXiv:1603.06544 (replaced) [pdf, ps, other]
Title: Nearest Points on Toric Varieties
Comments: 20 pages
Subjects: Algebraic Geometry (math.AG); Symbolic Computation (cs.SC); Optimization and Control (math.OC)
[152]  arXiv:1605.07084 (replaced) [pdf, ps, other]
Title: Low-Sensitivity Functions from Unambiguous Certificates
Comments: 25 pages. This version expands the results and adds Pooya Hatami and Avishay Tal as authors
Subjects: Computational Complexity (cs.CC); Quantum Physics (quant-ph)
[153]  arXiv:1609.01885 (replaced) [pdf, other]
Title: DAiSEE: Towards User Engagement Recognition in the Wild
Comments: 10 pages, 6 figures, 3 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG)
[154]  arXiv:1609.05834 (replaced) [pdf, other]
Title: On Support Relations and Semantic Scene Graphs
Comments: Accepted in ISPRS Journal of Photogrammetry and Remote Sensing
Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
[155]  arXiv:1612.00563 (replaced) [pdf, other]
Title: Self-critical Sequence Training for Image Captioning
Comments: CVPR 2017 + additional analysis + fixed baseline results, 16 pages
Subjects: Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
[156]  arXiv:1612.02346 (replaced) [pdf, other]
Title: Quotient inductive-inductive types
Subjects: Logic in Computer Science (cs.LO)
[157]  arXiv:1612.02542 (replaced) [pdf, other]
Title: Minimum Rates of Approximate Sufficient Statistics
Comments: To appear in the IEEE Transactions on Information Theory
Subjects: Information Theory (cs.IT); Statistics Theory (math.ST)
[158]  arXiv:1612.07003 (replaced) [pdf, other]
Title: Image biomarker standardisation initiative
Comments: 90 pages: changes from previous versions are detailed on pages 1 and 2
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[159]  arXiv:1701.02214 (replaced) [pdf, other]
Title: Accurate Learning or Fast Mixing? Dynamic Adaptability of Caching Algorithms
Comments: 51 pages, 17 figures
Subjects: Networking and Internet Architecture (cs.NI)
[160]  arXiv:1702.04458 (replaced) [pdf, other]
Title: Decentralized Baseband Processing for Massive MU-MIMO Systems
Comments: 16 pages; to appear in the IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS)
Subjects: Information Theory (cs.IT)
[161]  arXiv:1702.05743 (replaced) [pdf, other]
Title: DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing
Comments: Add the code link
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[162]  arXiv:1702.07956 (replaced) [pdf, ps, other]
Title: Generative Adversarial Active Learning
Subjects: Learning (cs.LG); Machine Learning (stat.ML)
[163]  arXiv:1702.08193 (replaced) [pdf, other]
Title: Modularisation of Sequent Calculi for Normal and Non-normal Modalities
Subjects: Logic in Computer Science (cs.LO); Logic (math.LO)
[164]  arXiv:1703.00410 (replaced) [pdf, other]
Title: Detecting Adversarial Samples from Artifacts
Comments: Submitted to ICML 2017
Subjects: Machine Learning (stat.ML); Learning (cs.LG)
[165]  arXiv:1703.02403 (replaced) [pdf, other]
Title: On Structured Prediction Theory with Calibrated Convex Surrogate Losses
Comments: Appears in: Advances in Neural Information Processing Systems 30 (NIPS 2017). 30 pages
Subjects: Learning (cs.LG); Machine Learning (stat.ML)
[166]  arXiv:1703.05830 (replaced) [pdf, other]
Title: Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
Subjects: Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG)
[167]  arXiv:1703.07656 (replaced) [pdf, other]
Title: Randomizing growing networks with a time-respecting null model
Comments: 13 pages, 10 figures
Subjects: Physics and Society (physics.soc-ph); Digital Libraries (cs.DL); Social and Information Networks (cs.SI); Data Analysis, Statistics and Probability (physics.data-an)
[168]  arXiv:1703.09499 (replaced) [pdf, ps, other]
Title: Locality preserving projection on SPD matrix Lie group: algorithm and analysis
Comments: 15 pages, 3 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV); Numerical Analysis (cs.NA)
[169]  arXiv:1703.10675 (replaced) [pdf, other]
Title: Applying Ricci Flow to High Dimensional Manifold Learning
Comments: 18 pages, 4 figure
Subjects: Learning (cs.LG)
[170]  arXiv:1704.01361 (replaced) [pdf, other]
Title: Applications of position-based coding to classical communication over quantum channels
Comments: v3: 40 pages, v3 includes an inequality relating Petz-Renyi relative entropy to hypothesis testing relative entropy and a new simultaneous decoding achievable rate region in terms of conditional collision quantum entropies
Subjects: Quantum Physics (quant-ph); Information Theory (cs.IT)
[171]  arXiv:1704.02450 (replaced) [pdf, other]
Title: Coupled Deep Learning for Heterogeneous Face Recognition
Comments: AAAI 2018
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[172]  arXiv:1704.08934 (replaced) [pdf, ps, other]
Title: A lower bound on CNF encodings of the at-most-one constraint
Comments: 35 pages, version 2 contains a relatively large number of changes, the purpose of most of them is a better presentation, however, there are also minor improvements in the obtained bounds
Subjects: Computational Complexity (cs.CC)
[173]  arXiv:1705.01781 (replaced) [pdf, other]
Title: Am I Done? Predicting Action Progress in Videos
Comments: Submitted to CVPR 2018
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[174]  arXiv:1705.06995 (replaced) [pdf, other]
Title: Nearly second-order asymptotic optimality of sequential change-point detection with one-sample updates
Subjects: Statistics Theory (math.ST); Learning (cs.LG)
[175]  arXiv:1705.08775 (replaced) [pdf, ps, other]
Title: A Control Performance Index for Multicopters Under Off-nominal Conditions
Comments: 9 pages, 5 figures
Subjects: Robotics (cs.RO)
[176]  arXiv:1706.00827 (replaced) [pdf, other]
Title: Multi-Class Model Fitting by Energy Minimization and Mode-Seeking
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[177]  arXiv:1706.00984 (replaced) [pdf, other]
Title: Graph-Cut RANSAC
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[178]  arXiv:1706.01987 (replaced) [pdf, other]
Title: ChemKED: a human- and machine-readable data standard for chemical kinetics experiments
Comments: 22 pages, accepted for publication in the International Journal of Chemical Kinetics
Subjects: Chemical Physics (physics.chem-ph); Computational Engineering, Finance, and Science (cs.CE)
[179]  arXiv:1706.07179 (replaced) [pdf, other]
Title: RelNet: End-to-End Modeling of Entities & Relations
Comments: Accepted in AKBC 2017
Subjects: Computation and Language (cs.CL); Learning (cs.LG)
[180]  arXiv:1706.07845 (replaced) [pdf, other]
Title: HARP: Hierarchical Representation Learning for Networks
Comments: To appear in AAAI 2018
Subjects: Social and Information Networks (cs.SI)
[181]  arXiv:1707.00798 (replaced) [pdf, other]
Title: Deep Representation Learning with Part Loss for Person Re-Identification
Comments: 9 pages, 9 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[182]  arXiv:1707.01816 (replaced) [pdf, other]
Title: Common Counterfactual Belief of Rationality Subsumes Superrationality On Symmetric Games
Authors: Ghislain Fourny
Comments: 14 pages
Subjects: Computer Science and Game Theory (cs.GT)
[183]  arXiv:1707.01922 (replaced) [pdf, other]
Title: Zero-Shot Deep Domain Adaptation
Comments: 8 pages, 4 figures, 7 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[184]  arXiv:1707.02427 (replaced) [pdf, other]
Title: Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection
Comments: Accepted for publication at German Conference on Pattern Recognition (GCPR) 2017. This research was supported by German Research Foundation DFG within Priority Research Programme 1894 "Volunteered Geographic Information: Interpretation, Visualisation and Social Computing"
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[185]  arXiv:1708.00602 (replaced) [pdf, other]
Title: Phase Retrieval From Binary Measurements
Subjects: Information Theory (cs.IT)
[186]  arXiv:1708.04896 (replaced) [pdf, other]
Title: Random Erasing Data Augmentation
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[187]  arXiv:1708.05690 (replaced) [pdf, other]
Title: Modeling Spread of Preferences in Social Networks for Sampling-based Preference Aggregation
Comments: The original version of this paper is accepted for publication in IEEE Transactions on Network Science and Engineering. The copyright for this article belongs to IEEE
Subjects: Social and Information Networks (cs.SI); Physics and Society (physics.soc-ph)
[188]  arXiv:1708.05929 (replaced) [pdf, other]
Title: Explaining Anomalies in Groups with Characterizing Subspace Rules
Comments: 17 pages, 6 figures, 8 tables
Subjects: Learning (cs.LG); Machine Learning (stat.ML)
[189]  arXiv:1708.06010 (replaced) [pdf, other]
Title: The Universal Process
Authors: Yuxi Fu
Subjects: Logic in Computer Science (cs.LO)
[190]  arXiv:1709.05125 (replaced) [pdf, other]
Title: Generalized Internal Boundaries (GIB)
Subjects: Fluid Dynamics (physics.flu-dyn); Numerical Analysis (cs.NA); Computational Physics (physics.comp-ph)
[191]  arXiv:1709.05475 (replaced) [pdf, other]
Title: Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification
Comments: Accepted by Interspeech 2017
Subjects: Computation and Language (cs.CL)
[192]  arXiv:1709.05633 (replaced) [pdf]
Title: An Ultralow Leakage Synaptic Scaling Homeostatic Plasticity Circuit With Configurable Time Scales up to 100 ks
Subjects: Emerging Technologies (cs.ET)
[193]  arXiv:1709.05910 (replaced) [pdf, other]
Title: Learning a Fully Convolutional Network for Object Recognition using very few Data
Comments: Submitted to ICRA 2018. This research was supported by German Research Foundation DFG within Priority Research Programme 1894 "Volunteered Geographic Information: Interpretation, Visualisation and Social Computing"
Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
[194]  arXiv:1709.08339 (replaced) [pdf]
Title: Machine Learning for Networking: Workflow, Advances and Opportunities
Comments: 8 pages, 2 figures
Subjects: Networking and Internet Architecture (cs.NI)
[195]  arXiv:1709.09268 (replaced) [pdf, other]
Title: FSL-BM: Fuzzy Supervised Learning with Binary Meta-Feature for Classification
Comments: FICC2018
Subjects: Learning (cs.LG); Artificial Intelligence (cs.AI)
[196]  arXiv:1710.00528 (replaced) [pdf, ps, other]
Title: Plethysm and fast matrix multiplication
Authors: Tim Seynnaeve
Comments: 5 pages
Subjects: Representation Theory (math.RT); Computational Complexity (cs.CC)
[197]  arXiv:1710.04584 (replaced) [pdf, ps, other]
Title: Towards Scalable Spectral Clustering via Spectrum-Preserving Sparsification
Subjects: Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
[198]  arXiv:1710.06026 (replaced) [pdf, other]
Title: Targeting Interventions in Networks
Comments: typos fixed, mainly having to do with the sign of K in section 5.1
Subjects: Computer Science and Game Theory (cs.GT)
[199]  arXiv:1710.06061 (replaced) [pdf, other]
Title: Reply With: Proactive Recommendation of Email Attachments
Comments: CIKM2017. Proceedings of the 26th ACM International Conference on Information and Knowledge Management. 2017
Subjects: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
[200]  arXiv:1710.08312 (replaced) [pdf, other]
Title: Attending to All Mention Pairs for Full Abstract Biological Relation Extraction
Comments: 6th Workshop on Automated Knowledge Base Construction (AKBC)
Subjects: Computation and Language (cs.CL)
[201]  arXiv:1710.08864 (replaced) [pdf, other]
Title: One pixel attack for fooling deep neural networks
Subjects: Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
[202]  arXiv:1710.10296 (replaced) [pdf]
Title: The implementation of a Deep Recurrent Neural Network Language Model on a Xilinx FPGA
Subjects: Neural and Evolutionary Computing (cs.NE); Hardware Architecture (cs.AR)
[203]  arXiv:1710.10468 (replaced) [pdf, other]
Title: Speaker Diarization with LSTM
Comments: Submitted to ICASSP 2018
Subjects: Audio and Speech Processing (eess.AS); Learning (cs.LG); Sound (cs.SD); Machine Learning (stat.ML)
[204]  arXiv:1710.11298 (replaced) [pdf, ps, other]
Title: Effective Tensor Sketching via Sparsification
Authors: Dong Xia, Ming Yuan
Subjects: Methodology (stat.ME); Information Theory (cs.IT); Numerical Analysis (cs.NA); Machine Learning (stat.ML)
[205]  arXiv:1710.11550 (replaced) [html]
Title: Proceedings of the Data For Good Exchange 2017
Authors: Philipp Meerkamp
Subjects: Computers and Society (cs.CY)
[206]  arXiv:1711.00066 (replaced) [pdf, other]
Title: Fraternal Dropout
Comments: Added official GitHub code for replication. Added references. Corrected typos
Subjects: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Learning (cs.LG)
[207]  arXiv:1711.00648 (replaced) [pdf, ps, other]
Title: Data Augmentation in Emotion Classification using Generative Adversarial Networks
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[208]  arXiv:1711.01434 (replaced) [pdf]
Title: Transaction Fraud Detection Using GRU-centered Sandwich-structured Model
Comments: submitted to cscwd2018
Subjects: Cryptography and Security (cs.CR); Learning (cs.LG)
[209]  arXiv:1711.01938 (replaced) [pdf, other]
Title: Single-Carrier Modulation versus OFDM for Millimeter-Wave Wireless MIMO
Comments: accepted for publication on IEEE Transactions on Communications
Subjects: Information Theory (cs.IT); Networking and Internet Architecture (cs.NI)
[210]  arXiv:1711.02520 (replaced) [pdf, other]
Title: End-to-end learning for music audio tagging at scale
Comments: In proceedings of the Workshop on Machine Learning for Audio Signal Processing (ML4Audio) at NIPS 2017. Code: this https URL Demo: this http URL
Subjects: Sound (cs.SD); Audio and Speech Processing (eess.AS)
[211]  arXiv:1711.03050 (replaced) [pdf, other]
Title: Correctness of Speculative Optimizations with Dynamic Deoptimization
Subjects: Programming Languages (cs.PL)
[212]  arXiv:1711.04161 (replaced) [pdf, other]
Title: End-to-end Video-level Representation Learning for Action Recognition
Comments: 10 pages, 6 figures, 6 tables
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[213]  arXiv:1711.04184 (replaced) [pdf, ps, other]
Title: Real-number Computability from the Perspective of Computer Assisted Proofs in Analysis
Subjects: Logic in Computer Science (cs.LO); Computational Complexity (cs.CC)
[214]  arXiv:1711.04204 (replaced) [pdf, other]
Title: Commonsense LocatedNear Relation Extraction
Comments: 6 pages + 2 pages of reference. Accepted by AKBC@NIPS'17
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
[215]  arXiv:1711.04289 (replaced) [pdf, other]
Title: Natural Language Inference with External Knowledge
Comments: Submitted to ICLR 2018
Subjects: Computation and Language (cs.CL)
[216]  arXiv:1711.04291 (replaced) [pdf, other]
Title: Scale out for large minibatch SGD: Residual network training on ImageNet-1K with improved accuracy and reduced time to train
Comments: 10 pages, 4 figures, 13 tables
Subjects: Machine Learning (stat.ML); Learning (cs.LG)
[217]  arXiv:1711.04322 (replaced) [pdf, other]
Title: Gender recognition and biometric identification using a large dataset of hand images
Authors: Mahmoud Afifi
Comments: 22 pages, 4 figures, 5 tables, under consideration at Pattern Recognition Letters
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[218]  arXiv:1711.04851 (replaced) [pdf, other]
Title: Learning and Visualizing Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes
Comments: Presented at NIPS 2017 Symposium on Interpretable Machine Learning
Subjects: Machine Learning (stat.ML); Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG)
[219]  arXiv:1711.04853 (replaced) [pdf, other]
Title: Denoising Imaging Polarimetry by an Adapted BM3D Method
Authors: Alexander B. Tibbs (1 and 2), Ilse M. Daly (2), Nicholas W. Roberts (2), David R. Bull (1) ((1) Department of Electrical and Electronic Engineering, University of Bristol, (2) School of Biological Sciences, University of Bristol)
Subjects: Computer Vision and Pattern Recognition (cs.CV)
[220]  arXiv:1711.05147 (replaced) [pdf, other]
Title: Restoration by Compression
Subjects: Information Theory (cs.IT)
[221]  arXiv:1711.05376 (replaced) [pdf, other]
Title: Sliced Wasserstein Distance for Learning Gaussian Mixture Models
Subjects: Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG); Machine Learning (stat.ML)
[222]  arXiv:1711.05380 (replaced) [pdf, other]
Title: Bridging Source and Target Word Embeddings for Neural Machine Translation
Comments: 8 pages, 6 figures
Subjects: Computation and Language (cs.CL)
[223]  arXiv:1711.05411 (replaced) [pdf, other]
Title: Z-Forcing: Training Stochastic Recurrent Networks
Comments: To appear in NIPS'17
Subjects: Machine Learning (stat.ML); Learning (cs.LG)
[224]  arXiv:1711.05429 (replaced) [pdf]
Title: Modular Resource Centric Learning for Workflow Performance Prediction
Comments: This paper was presented at: 6th Workshop on Big Data Analytics: Challenges, and Opportunities (BDAC) at the 27th IEEE/ACM International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2015)
Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Learning (cs.LG)
[225]  arXiv:1711.05541 (replaced) [pdf, other]
Title: Good and safe uses of AI Oracles
Authors: Stuart Armstrong
Comments: 11 pages, 2 figures
Subjects: Artificial Intelligence (cs.AI)
[226]  arXiv:1711.05572 (replaced) [pdf, other]
Title: Mitigating Clipping Effects on Error Floors under Belief Propagation Decoding of Polar Codes
Subjects: Information Theory (cs.IT)
[227]  arXiv:1711.05573 (replaced) [pdf, other]
Title: PlinyCompute: A Platform for High-Performance, Distributed, Data-Intensive Tool Development
Comments: 48 pages, including references and Appendix
Subjects: Databases (cs.DB); Distributed, Parallel, and Cluster Computing (cs.DC)
[228]  arXiv:1711.05683 (replaced) [pdf, other]
Title: Hydra: a C++11 framework for data analysis in massively parallel platforms
Comments: ACAT 2017 Proceedings
Subjects: Mathematical Software (cs.MS); High Energy Physics - Experiment (hep-ex); Computational Physics (physics.comp-ph); Data Analysis, Statistics and Probability (physics.data-an)
[229]  arXiv:1711.05697 (replaced) [pdf, other]
Title: Motif-based Convolutional Neural Network on Graphs
Subjects: Learning (cs.LG); Social and Information Networks (cs.SI)
[ total of 229 entries: 1-229 ]
[ showing up to 2000 entries per page: fewer | more ]

Disable MathJax (What is MathJax?)