total 2009took 0.14s

A feasibility study of deep neural networks for the recognition of banknotes regarding central bank requirementsJul 18 2019This paper contains a feasibility study of deep neural networks for the classification of Euro banknotes with respect to requirements of central banks on the ATM and high speed sorting industry. Instead of concentrating on the accuracy for a large number ... More

Band-structure and electronic transport calculations in cylindrical wires : the issue of bound states in transfer-matrix calculationsJul 16 2019The transfer-matrix methodology is used to solve linear systems of differential equations, such as those that arise when solving Schr\"odinger's equation, in situations where the solutions of interest are in the continuous part of the energy spectrum. ... More

Deep learning-based color holographic microscopyJul 15 2019We report a framework based on a generative adversarial network (GAN) that performs high-fidelity color image reconstruction using a single hologram of a sample that is illuminated simultaneously by light at three different wavelengths. The trained network ... More

Quick, Stat!: A Statistical Analysis of the Quick, Draw! DatasetJul 15 2019The Quick, Draw! Dataset is a Google dataset with a collection of 50 million drawings, divided in 345 categories, collected from the users of the game Quick, Draw!. In contrast with most of the existing image datasets, in the Quick, Draw! Dataset, drawings ... More

Learning better generative models for dexterous, single-view grasping of novel objectsJul 13 2019This paper concerns the problem of how to learn to grasp dexterously, so as to be able to then grasp novel objects seen only from a single view-point. Recently, progress has been made in data-efficient learning of generative grasp models which transfer ... More

On linear regression in three-dimensional Euclidean spaceJul 13 2019The three-dimensional linear regression problem is a problem of finding a spacial straight line best fitting a group of points in three-dimensional Euclidean space. This problem is considered in the present paper and a solution to it is given in a coordinate-free ... More

Gravitational-wave parameter estimation with gaps in LISA: a Bayesian data augmentation methodJul 10 2019By listening to gravity in the low frequency band, between 0.1 mHz and 1 Hz, the future space-based gravitational-wave observatory LISA will be able to detect tens of thousands of astrophysical sources from cosmic dawn to the present. The detection and ... More

Discontinuous Galerkin discretization for two-equation turbulence closure modelJul 10 2019Accurate representation of vertical turbulence is crucial for numerical ocean modelling, both in global and coastal applications. The state-of-the-art approach is to use two-equation turbulence closure models which introduces two dynamic equations to ... More

Applications of a Novel Knowledge Discovery and Data Mining Process Model for MetabolomicsJul 09 2019This work demonstrates the execution of a novel process model for knowledge discovery and data mining for metabolomics (MeKDDaM). It aims to illustrate MeKDDaM process model applicability using four different real-world applications and to highlight its ... More

Computer-Aided Data Mining: Automating a Novel Knowledge Discovery and Data Mining Process Model for MetabolomicsJul 09 2019This work presents MeKDDaM-SAGA, computer-aided automation software for implementing a novel knowledge discovery and data mining process model that was designed for performing justifiable, traceable and reproducible metabolomics data analysis. The process ... More

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at ScaleJul 08 2019Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models. However, applications to science remain limited because of the impracticability of rewriting complex scientific ... More

Attentive Multi-Task Deep Reinforcement LearningJul 05 2019Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact ... More

Koalja: from Data Plumbing to Smart Workspaces in the Extended CloudJul 03 2019Koalja describes a generalized data wiring or `pipeline' platform, built on top of Kubernetes, for plugin user code. Koalja makes the Kubernetes underlay transparent to users (for a `serverless' experience), and offers a breadboarding experience for development ... More

Emergence of multiplicity of time scales in the modeling of climate, matter, life, and economyJul 01 2019We address dfferences between characteristic times in climate change and show the universal emergence of multiple time scales in material sciences, biomedicine and economics.

Quantile Regression Deep Reinforcement LearningJun 27 2019Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are limited by the ... More

A Winograd-based Integrated Photonics Accelerator for Convolutional Neural NetworksJun 25 2019Neural Networks (NNs) have become the mainstream technology in the artificial intelligence (AI) renaissance over the past decade. Among different types of neural networks, convolutional neural networks (CNNs) have been widely adopted as they have achieved ... More

Reserve Pricing in Repeated Second-Price Auctions with Strategic BiddersJun 21 2019We study revenue optimization learning algorithms for repeated second-price auctions with reserve where a seller interacts with multiple strategic bidders each of which holds a fixed private valuation for a good and seeks to maximize his expected future ... More

Privacy Preserving QoE Modeling using Collaborative LearningJun 21 2019Machine Learning based Quality of Experience (QoE) models potentially suffer from over-fitting due to limitations including low data volume, and limited participant profiles. This prevents models from becoming generic. Consequently, these trained models ... More

Privacy Preserving QoE Modeling using Collaborative LearningJun 21 2019Jun 26 2019Machine Learning based Quality of Experience (QoE) models potentially suffer from over-fitting due to limitations including low data volume, and limited participant profiles. This prevents models from becoming generic. Consequently, these trained models ... More

Theory of the Frequency Principle for General Deep Neural NetworksJun 21 2019Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal phenomenon of Frequency Principle (F-Principle): a DNN tends to learn a target function from low to high ... More

Theory of the Frequency Principle for General Deep Neural NetworksJun 21 2019Jul 02 2019Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal phenomenon of Frequency Principle (F-Principle): a DNN tends to learn a target function from low to high ... More

A Layered Aggregate Engine for Analytics WorkloadsJun 20 2019This paper introduces LMFAO (Layered Multiple Functional Aggregate Optimization), an in-memory optimization and execution engine for batches of aggregates over the input database. The primary motivation for this work stems from the observation that for ... More

Low-dimensional Embodied Semantics for Music and LanguageJun 20 2019Embodied cognition states that semantics is encoded in the brain as firing patterns of neural circuits, which are learned according to the statistical structure of human multimodal experience. However, each human brain is idiosyncratically biased, according ... More

Self-organized inductive reasoning with NeMuSJun 16 2019Neural Multi-Space (NeMuS) is a weighted multi-space representation for a portion of first-order logic designed for use with machine learning and neural network methods. It was demonstrated that it can be used to perform reasoning based on regions forming ... More

LioNets: Local Interpretation of Neural Networks through Penultimate Layer DecodingJun 15 2019Technological breakthroughs on smart homes, self-driving cars, health care and robotic assistants, in addition to reinforced law regulations, have critically influenced academic research on explainable machine learning. A sufficient number of researchers ... More

Deep neural network for fringe pattern filtering and normalisationJun 14 2019We propose a new framework for processing Fringe Patterns (FP). Our novel approach builds upon the hypothesis that the denoising and normalisation of FPs can be learned by a deep neural network if enough pairs of corrupted and cleaned FPs are provided. ... More

A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable GamesJun 13 2019We consider differentiable games: multi-objective minimization problems, where the goal is to find a Nash equilibrium. The machine learning community has recently started using extrapolation-based variants of the gradient method. A prime example is the ... More

A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable GamesJun 13 2019Jun 24 2019We consider differentiable games: multi-objective minimization problems, where the goal is to find a Nash equilibrium. The machine learning community has recently started using extrapolation-based variants of the gradient method. A prime example is the ... More

N-body Approach to the Traveling Salesman Problem (TSP)Jun 13 2019In the Traveling Salesman Problem (TSP), a list of cities and the distances between them are given. The goal is to find the shortest possible route that visits each city exactly once and returns to the original city. The TSP has a wide range of applications ... More

Meta-heuristic for non-homogeneous peak density spaces and implementation on 2 real-world parameter learning/tuning applicationsJun 13 2019Observer effect in physics (/psychology) regards bias in measurement (/perception) due to the interference of instrument (/knowledge). Based on these concepts, a new meta-heuristic algorithm is proposed for controlling memory usage per localities without ... More

Causal Inference in Higher Education: Building Better CurriculumsJun 11 2019Higher educational institutions constantly look for ways to meet students' needs and support them through graduation. Recent work in the field of learning analytics have developed methods for grade prediction and course recommendations. Although these ... More

LSTM Networks Can Perform Dynamic CountingJun 09 2019In this paper, we systematically assess the ability of standard recurrent networks to perform dynamic counting and to encode hierarchical representations. All the neural models in our experiments are designed to be small-sized networks both to prevent ... More

Kinetic Market Model: An Evolutionary AlgorithmJun 04 2019This research proposes the econophysics kinetic market model as an evolutionary algorithm's instance. The immediate results from this proposal is a new replacement rule for family competition genetic algorithms. It also represents a starting point to ... More

Adaptive Multimodal Music Learning via Interactive-haptic InstrumentJun 04 2019Haptic interfaces have untapped the sense of touch to assist multimodal music learning. We have recently seen various improvements of interface design on tactile feedback and force guidance aiming to make instrument learning more effective. However, most ... More

A Perspective on Objects and Systematic Generalization in Model-Based RLJun 03 2019In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the combinatorial construction ... More

Neural Network-based Object Classification by Known and Unknown Features (Based on Text Queries)Jun 03 2019The article presents a method that improves the quality of classification of objects described by a combination of known and unknown features. The method is based on modernized Informational Neurobayesian Approach with consideration of unknown features. ... More

Algorithmically generating new algebraic features of polynomial systems for machine learningJun 03 2019There are a variety of choices to be made in both computer algebra systems (CASs) and satisfiability modulo theory (SMT) solvers which can impact performance without affecting mathematical correctness. Such choices are candidates for machine learning ... More

Learning Patterns in Sample Distributions for Monte Carlo Variance ReductionJun 01 2019This paper investigates a novel a-posteriori variance reduction approach in Monte Carlo image synthesis. Unlike most established methods based on lateral filtering in the image space, our proposition is to produce the best possible estimate for each pixel ... More

Deep Learning Recommendation Model for Personalization and Recommendation SystemsMay 31 2019With the advent of deep learning, neural network-based recommendation models have emerged as an important tool for tackling personalization and recommendation tasks. These networks differ significantly from other deep learning networks due to their need ... More

PowerSGD: Practical Low-Rank Gradient Compression for Distributed OptimizationMay 31 2019We study gradient compression methods to alleviate the communication bottleneck in data-parallel distributed optimization. Despite the significant attention received, current compression schemes either do not scale well or fail to achieve the target test ... More

Memory-efficient and fast implementation of local adaptive binarization methodsMay 30 2019Binarization is widely used as an image preprocessing step to separate object especially text from background before recognition. For noisy images with uneven illumination, threshold values should be computed pixel by pixel to obtain a good segmentation. ... More

Memory-efficient and fast implementation of local adaptive binarization methodsMay 30 2019Jul 01 2019Binarization is widely used as an image preprocessing step to separate object especially text from background before recognition. For noisy images with uneven illumination such as degraded documents, threshold values need to be computed pixel by pixel ... More

On the Effectiveness of Low-rank Approximations for Collaborative Filtering compared to Neural NetworksMay 30 2019Even in times of deep learning, low-rank approximations by factorizing a matrix into user and item latent factors continue to be a method of choice for collaborative filtering tasks due to their great performance. While deep learning based approaches ... More

Clustering without Over-RepresentationMay 29 2019In this paper we consider clustering problems in which each point is endowed with a color. The goal is to cluster the points to minimize the classical clustering cost but with the additional constraint that no color is over-represented in any cluster. ... More

A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with OutliersMay 29 2019The Wahba problem, also known as rotation search, seeks to find the best rotation to align two sets of vector observations given putative correspondences, and is a fundamental routine in many computer vision and robotics applications. This work proposes ... More

Are Disentangled Representations Helpful for Abstract Visual Reasoning?May 29 2019A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world up-stream tasks, there is ... More

Asymptotically Unambitious Artificial General IntelligenceMay 29 2019General intelligence, the ability to solve arbitrary solvable problems, is supposed by many to be artificially constructible. Narrow intelligence, the ability to solve a given particularly difficult problem, has seen impressive recent development. Notable ... More

An Effective Multi-Resolution Hierarchical Granular Representation based Classifier using General Fuzzy Min-Max Neural NetworkMay 29 2019Jun 03 2019Motivated by the practical demands for simplification of data towards being consistent with human thinking and problem solving as well as tolerance of uncertainty, information granules are becoming important entities in data processing at different levels ... More

An Effective Multi-Resolution Hierarchical Granular Representation based Classifier using General Fuzzy Min-Max Neural NetworkMay 29 2019Motivated by the practical demands for simplification of data towards being consistent with human thinking and problem solving as well as tolerance of uncertainty, information granules are becoming important entities in data processing at different levels ... More

SignalTrain: Profiling Audio Compressors with Deep Neural NetworksMay 28 2019May 30 2019In this work we present a data-driven approach for predicting the behavior of (i.e., profiling) a given non-linear audio signal processing effect (henceforth "audio effect"). Our objective is to learn a mapping function that maps the unprocessed audio ... More

SignalTrain: Profiling Audio Compressors with Deep Neural NetworksMay 28 2019In this work we present a data-driven approach for predicting the behavior of (i.e., profiling) a given non-linear audio signal processing effect (henceforth "audio effect"). Our objective is to learn a mapping function that maps the unprocessed audio ... More

SAI: a Sensible Artificial Intelligence that plays with handicap and targets high scores in 9x9 Go (extended version)May 26 2019Jun 22 2019We develop a new model that can be applied to any perfect information two-player zero-sum game to target a high score, and thus a perfect play. We integrate this model into the Monte Carlo tree search-policy iteration learning pipeline introduced by Google ... More

Adversarial Policies: Attacking Deep Reinforcement LearningMay 25 2019Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another agent's observations. ... More

Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural NetworksMay 24 2019It remains a puzzle that why deep neural networks (DNNs), with more parameters than samples, often generalize well. An attempt of understanding this puzzle is to discover implicit biases underlying the training process of DNNs, such as the Frequency Principle ... More

Embedded Meta-Learning: Toward more flexible deep-learning modelsMay 23 2019How can deep learning systems flexibly reuse their knowledge? Toward this goal, we propose a new class of challenges, and a class of architectures that can solve them. The challenges are meta-mappings, which involve systematically transforming task behaviors ... More

Eigen Artificial Neural NetworksMay 22 2019This work has its origin in intuitive physical and statistical considerations. An artificial neural network is treated as a physical system, composed of a conservative vector force field. The derived scalar potential is a measure of the potential energy ... More

Stochastic Inverse Reinforcement LearningMay 21 2019Inverse reinforcement learning (IRL) is an ill-posed inverse problem since expert demonstrations may infer many solutions of reward functions which is hard to recover by local search methods such as a gradient method. In this paper, we generalize the ... More

Stochastic Inverse Reinforcement LearningMay 21 2019Jun 26 2019Inverse reinforcement learning (IRL) is an ill-posed inverse problem since expert demonstrations may infer many solutions of reward functions which is hard to recover by local search methods such as a gradient method. In this paper, we generalize the ... More

A type of generalization error induced by initialization in deep neural networksMay 19 2019How different initializations and loss functions affect the learning of a deep neural network (DNN), specifically its generalization error, is an important problem in practice. In this work, focusing on regression problems, we develop a kernel-norm minimization ... More

DeepSwarm: Optimising Convolutional Neural Networks using Swarm IntelligenceMay 17 2019In this paper we propose DeepSwarm, a novel neural architecture search (NAS) method based on Swarm Intelligence principles. At its core DeepSwarm uses Ant Colony Optimization (ACO) to generate ant population which uses the pheromone information to collectively ... More

Significance of parallel computing on the performance of Digital Image Correlation algorithms in MATLABMay 15 2019Digital Image Correlation (DIC) is a powerful tool used to evaluate displacements and deformations in a non-intrusive manner. By comparing two images, one of the undeformed reference state of a specimen and another of the deformed target state, the relative ... More

DeepFlow: History Matching in the Space of Deep Generative ModelsMay 14 2019Jun 12 2019The calibration of a reservoir model with observed transient data of fluid pressures and rates is a key task in obtaining a predictive model of the flow and transport behaviour of the earth's subsurface. The model calibration task, commonly referred to ... More

DeepFlow: History Matching in the Space of Deep Generative ModelsMay 14 2019The calibration of a reservoir model with observed transient data of fluid pressures and rates is a key task in obtaining a predictive model of the flow and transport behaviour of the earth's subsurface. The model calibration task, commonly referred to ... More

Learning to EvolveMay 08 2019Evolution and learning are two of the fundamental mechanisms by which life adapts in order to survive and to transcend limitations. These biological phenomena inspired successful computational methods such as evolutionary algorithms and deep learning. ... More

Object Exchangeability in Reinforcement Learning: Extended AbstractMay 07 2019Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. ... More

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social ContextsMay 06 2019Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations ... More

Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite ImageryMay 04 2019Millions of people worldwide are absent from their country's census. Accurate, current, and granular population metrics are critical to improving government allocation of resources, to measuring disease control, to responding to natural disasters, and ... More

Fundamental properties of transition-metals-adsorbed grapheneMay 03 2019The revealing properties of transition metal (T)-doped graphene systems are investigated with the use of the first-principles method. The detailed calculations cover the bond length, position and height of adatoms, binding energy, atom-dominated band ... More

Deep Learning for Audio Signal ProcessingApr 30 2019Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order ... More

Deep Learning for Audio Signal ProcessingApr 30 2019May 25 2019Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order ... More

Detecting Reflections by Combining Semantic and Instance SegmentationApr 30 2019Reflections in natural images commonly cause false positives in automated detection systems. These false positives can lead to significant impairment of accuracy in the tasks of detection, counting and segmentation. Here, inspired by the recent panoptic ... More

A neural network based on SPD manifold learning for skeleton-based hand gesture recognitionApr 29 2019This paper proposes a new neural network based on SPD manifold learning for skeleton-based hand gesture recognition. Given the stream of hand's joint positions, our approach combines two aggregation processes on respectively spatial and temporal domains. ... More

Deep-IRT: Make Deep Learning Based Knowledge Tracing Explainable Using Item Response TheoryApr 26 2019Deep learning based knowledge tracing model has been shown to outperform traditional knowledge tracing model without the need for human-engineered features, yet its parameters and representations have long been criticized for not being explainable. In ... More

Comparing machine learning models to choose the variable ordering for cylindrical algebraic decompositionApr 24 2019There has been recent interest in the use of machine learning (ML) approaches within mathematical software to make choices that impact on the computing performance without affecting the mathematical correctness of the result. We address the problem of ... More

Comparing machine learning models to choose the variable ordering for cylindrical algebraic decompositionApr 24 2019Jun 05 2019There has been recent interest in the use of machine learning (ML) approaches within mathematical software to make choices that impact on the computing performance without affecting the mathematical correctness of the result. We address the problem of ... More

Generated Loss and Augmented Training of MNIST VAEApr 24 2019The variational autoencoder (VAE) framework is a popular option for training unsupervised generative models, featuring ease of training and latent representation of data. The objective function of VAE does not guarantee to achieve the latter, however, ... More

Generated Loss, Augmented Training, and Multiscale VAEApr 23 2019The variational autoencoder (VAE) framework remains a popular option for training unsupervised generative models, especially for discrete data where generative adversarial networks (GANs) require workaround to create gradient for the generator. In our ... More

Crowdsourced Truth Discovery in the Presence of Hierarchies for Knowledge FusionApr 23 2019Existing works for truth discovery in categorical data usually assume that claimed values are mutually exclusive and only one among them is correct. However, many claimed values are not mutually exclusive even for functional predicates due to their hierarchical ... More

An image structure model for exact edge detectionApr 21 2019The paper presents a new model for single channel images low-level interpretation. The image is decomposed into a graph which captures a complete set of structural features. The description allows to accurately identify every edge location and its correct ... More

Self-Attention Graph PoolingApr 17 2019Apr 24 2019Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution ... More

Self-Attention Graph PoolingApr 17 2019Apr 18 2019Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution ... More

Self-Attention Graph PoolingApr 17 2019Jun 13 2019Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution ... More

Self-Attention Graph PoolingApr 17 2019Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution ... More

IAN: Combining Generative Adversarial Networks for Imaginative Face GenerationApr 16 2019Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the training set and that enables sampling from that domain and using the knowledge learned for useful applications. Several ... More

An Empirical Evaluation of Text Representation Schemes on Multilingual Social Web to Filter the Textual AggressionApr 16 2019This paper attempt to study the effectiveness of text representation schemes on two tasks namely: User Aggression and Fact Detection from the social media contents. In User Aggression detection, The aim is to identify the level of aggression from the ... More

Evaluating the Applicability of Bandwidth Allocation Models for EON Slot AllocationApr 16 2019Bandwidth Allocation Models (BAMs) configure and handle resource allocation (bandwidth, LSPs, fiber, slots) in networks in general (IP/MPLS/DS-TE, optical domain, other). In this paper, BAMs are considered for elastic optical networks slot allocation ... More

Detecting the Unexpected via Image ResynthesisApr 16 2019Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes ... More

Detecting the Unexpected via Image ResynthesisApr 16 2019Apr 17 2019Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes ... More

Influence of Control Parameters and the Size of Biomedical Image Datasets on the Success of Adversarial AttacksApr 15 2019In this paper, we study dependence of the success rate of adversarial attacks to the Deep Neural Networks on the biomedical image type, control parameters, and image dataset size. With this work, we are going to contribute towards accumulation of experimental ... More

Text2Node: a Cross-Domain System for Mapping Arbitrary Phrases to a TaxonomyApr 11 2019Electronic health record (EHR) systems are used extensively throughout the healthcare domain. However, data interchangeability between EHR systems is limited due to the use of different coding standards across systems. Existing methods of mapping coding ... More

Privacy protocolsApr 11 2019Security protocols enable secure communication over insecure channels. Privacy protocols enable private interactions over secure channels. Security protocols set up secure channels using cryptographic primitives. Privacy protocols set up private channels ... More

Segmentation of Skeletal Muscle in Thigh Dixon MRI Based on Texture AnalysisApr 09 2019Segmentation of skeletal muscles in Magnetic Resonance Images (MRI) is essential for the study of muscle physiology and diagnosis of muscular pathologies. However, manual segmentation of large MRI volumes is a time-consuming task. The state-of-the-art ... More

Towards Analyzing Semantic Robustness of Deep Neural NetworksApr 09 2019Despite the impressive performance of Deep Neural Networks (DNNs) on various vision tasks, they still exhibit erroneous high sensitivity toward semantic primitives (e.g. object pose). We propose a theoretically grounded analysis for DNNs robustness in ... More

Scaling Up Collaborative Filtering Data Sets through Randomized Fractal ExpansionsApr 08 2019Recommender system research suffers from a disconnect between the size of academic data sets and the scale of industrial production systems. In order to bridge that gap, we propose to generate large-scale user/item interaction data sets by expanding pre-existing ... More

Comparative Analysis of Automatic Skin Lesion Segmentation with Two Different ImplementationsApr 05 2019Lesion segmentation from the surrounding skin is the first task for developing automatic Computer-Aided Diagnosis of skin cancer. Variant features of lesion like uneven distribution of color, irregular shape, border and texture make this task challenging. ... More

Continuous Direct Sparse Visual Odometry from RGB-D ImagesApr 03 2019May 21 2019This paper reports on a novel formulation and evaluation of visual odometry from RGB-D images. Assuming a static scene, the developed theoretical framework generalizes the widely used direct energy formulation (photometric error minimization) technique ... More

Unsupervised Continual Learning and Self-Taught Associative Memory HierarchiesApr 03 2019We first pose the Unsupervised Continual Learning (UCL) problem: learning salient representations from a non-stationary stream of unlabeled data in which the number of object classes varies with time. Given limited labeled data just before inference, ... More

A Dynamic Routing Framework for Shared Mobility ServicesMar 26 2019Travel time in urban centers is a significant contributor to the quality of living of its citizens. Mobility on Demand (MoD) services such as Uber and Lyft have revolutionized the transportation infrastructure, enabling new solutions for passengers. Shared ... More

A data-driven approach to precipitation parameterizations using convolutional encoder-decoder neural networksMar 25 2019Numerical Weather Prediction (NWP) models represent sub-grid processes using parameterizations, which are often complex and a major source of uncertainty in weather forecasting. In this work, we devise a simple machine learning (ML) methodology to learn ... More

Network Horizon Dynamics I: Qualitative AspectsMar 25 2019Mostly acyclic directed networks, treated mathematically as directed graphs, arise in machine learning, biology, social science, physics, and other applications. Newman [1] has noted the mathematical challenges of such networks. In this series of papers, ... More