total 753took 0.13s

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

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

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

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

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

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

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

Combining Model and Parameter Uncertainty in Bayesian Neural NetworksMar 18 2019Mar 20 2019Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using Bayesian approach: ... More

Combining Model and Parameter Uncertainty in Bayesian Neural NetworksMar 18 2019Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using Bayesian approach: ... More

Multi-Stage Fault Warning for Large Electric Grids Using Anomaly Detection and Machine LearningMar 15 2019In the monitoring of a complex electric grid, it is of paramount importance to provide operators with early warnings of anomalies detected on the network, along with a precise classification and diagnosis of the specific fault type. In this paper, we ... More

Sparse Grouped Gaussian Processes for Solar Power ForecastingMar 10 2019We consider multi-task regression models where observations are assumed to be a linear combination of several latent node and weight functions, all drawn from Gaussian process priors that allow nonzero covariance between grouped latent functions. Motivated ... More

Only Connect, SecurelyMar 07 2019The lattice model proposed by Denning in her seminal work provided secure information flow analyses with an intuitive and uniform mathematical foundation. Different organisations, however, may employ quite different security lattices. In this paper, we ... More

Socially-Aware Congestion Control in Ad-Hoc Networks: Current Status and The Way ForwardMar 03 2019Ad-hoc social networks (ASNETs) represent a special type of traditional ad-hoc network in which a user's social properties (such as the social connections and communications metadata as well as application data) are leveraged for offering enhanced services ... More

Minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexityFeb 27 2019An adaptive regularization algorithm using inexact function and derivatives evaluations is proposed for the solution of composite nonsmooth nonconvex optimization. It is shown that this algorithm needs at most $O(|\log(\epsilon)|\,\epsilon^{-2})$ evaluations ... More

Parallel Rendering and Large Data VisualizationFeb 23 2019We are living in the big data age: An ever increasing amount of data is being produced through data acquisition and computer simulations. While large scale analysis and simulations have received significant attention for cloud and high-performance computing, ... More

Local minimax rates for closeness testing of discrete distributionsFeb 01 2019We consider the closeness testing (or two-sample testing) problem in the Poisson vector model - which is known to be asymptotically equivalent to the model of multinomial distributions. The goal is to distinguish whether two data samples are drawn from ... More

Hyperbox based machine learning algorithms: A comprehensive surveyJan 31 2019Feb 04 2019With the rapid development of digital information, the data volume generated by humans and machines is growing exponentially. Along with this trend, machine learning algorithms have been formed and evolved continuously to discover new information and ... More

Hyperbox based machine learning algorithms: A comprehensive surveyJan 31 2019Mar 22 2019With the rapid development of digital information, the data volume generated by humans and machines is growing exponentially. Along with this trend, machine learning algorithms have been formed and evolved continuously to discover new information and ... More

The CM Algorithm for the Maximum Mutual Information Classifications of Unseen InstancesJan 28 2019The Maximum Mutual Information (MMI) criterion is different from the Least Error Rate (LER) criterion. It can reduce failing to report small probability events. This paper introduces the Channels Matching (CM) algorithm for the MMI classifications of ... More

The Use of Unlabeled Data versus Labeled Data for Stopping Active Learning for Text ClassificationJan 26 2019Annotation of training data is the major bottleneck in the creation of text classification systems. Active learning is a commonly used technique to reduce the amount of training data one needs to label. A crucial aspect of active learning is determining ... More

Stopping Active Learning based on Predicted Change of F Measure for Text ClassificationJan 26 2019During active learning, an effective stopping method allows users to limit the number of annotations, which is cost effective. In this paper, a new stopping method called Predicted Change of F Measure will be introduced that attempts to provide the users ... More

Scalable Realistic Recommendation Datasets through Fractal ExpansionsJan 23 2019Feb 20 2019Recommender System research suffers currently 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 more massive user/item interaction data sets by expanding ... More

Embedding quadratization gadgets on Chimera and Pegasus graphsJan 23 2019We group all known quadratizations of cubic and quartic terms in binary optimization problems into six and seven unique graphs respectively. We then perform a minor embedding of these graphs onto the well-known Chimera graph, and the brand new Pegasus ... More

Pegasus: The second connectivity graph for large-scale quantum annealing hardwareJan 22 2019Pegasus is a graph which offers substantially increased connectivity between the qubits of quantum annealing hardware compared to the graph Chimera. It is the first fundamental change in the connectivity graph of quantum annealers built by D-Wave since ... More

Quadratization in discrete optimization and quantum mechanicsJan 14 2019A book about turning high-degree optimization problems into quadratic optimization problems that maintain the same global minimum (ground state). This book explores quadratizations for pseudo-Boolean optimization, perturbative gadgets used in QMA completeness ... More

ChronoMID - Cross-Modal Neural Networks for 3-D Temporal Medical Imaging DataJan 12 2019ChronoMID builds on the success of cross-modal convolutional neural networks (X-CNNs), making the novel application of the technique to medical imaging data. Specifically, this paper presents and compares alternative approaches - timestamps and difference ... More

On Huang and Wong's Algorithm for Generalized Binary Split TreesJan 12 2019Huang and Wong [5] proposed a polynomial-time dynamic-programming algorithm for computing optimal generalized binary split trees. We show that their algorithm is incorrect. Thus, it remains open whether such trees can be computed in polynomial time. Spuler ... More

An Evaluation of Methods for Real-Time Anomaly Detection using Force Measurements from the Turning ProcessDec 20 2018We examined the use of three conventional anomaly detection methods and assess their potential for on-line tool wear monitoring. Through efficient data processing and transformation of the algorithm proposed here, in a real-time environment, these methods ... More

On balanced clustering with tree-like structures over clustersDec 09 2018The article addresses balanced clustering problems with an additional requirement as a tree-like structure over the obtained balanced clusters. This kind of clustering problems can be useful in some applications (e.g., network design, management and routing). ... More

A note on solving nonlinear optimization problems in variable precisionDec 09 2018Dec 11 2018This short note considers an efficient variant of the trust-region algorithm with dynamic accuracy proposed Carter (1993) and Conn, Gould and Toint (2000) as a tool for very high-performance computing, an area where it is critical to allow multi-precision ... More

A note on solving nonlinear optimization problems in variable precisionDec 09 2018Apr 12 2019This short note considers an efficient variant of the trust-region algorithm with dynamic accuracy proposed Carter (1993) and Conn, Gould and Toint (2000) as a tool for very high-performance computing, an area where it is critical to allow multi-precision ... More

Naive Dictionary On Musical Corpora: From Knowledge Representation To Pattern RecognitionNov 29 2018In this paper, we propose and develop the novel idea of treating musical sheets as literary documents in the traditional text analytics parlance, to fully benefit from the vast amount of research already existing in statistical text mining and topic modelling. ... More

The MeSH-gram Neural Network Model: Extending Word Embedding Vectors with MeSH Concepts for UMLS Semantic Similarity and Relatedness in the Biomedical DomainNov 28 2018Eliciting semantic similarity between concepts in the biomedical domain remains a challenging task. Recent approaches founded on embedding vectors have gained in popularity as they risen to efficiently capture semantic relationships The underlying idea ... More

The value of forecasts: Quantifying the economic gains of accurate quarter-hourly electricity price forecastsNov 21 2018We propose a multivariate elastic net regression forecast model for German quarter-hourly electricity spot markets. While the literature is diverse on day-ahead prediction approaches, both the intraday continuous and intraday call-auction prices have ... More

Stochastic Algorithmic Differentiation of (Expectations of) Discontinuous Functions (Indicator Functions)Nov 14 2018Nov 26 2018In this paper we present a method for the accurate estimation of the derivative (aka.~sensitivity) of expectations of functions involving an indicator function by combining a stochastic algorithmic differentiation and a regression. The method is an improvement ... More

Time-interval balancing in multi-processor scheduling of composite modular jobs (preliminary description)Nov 11 2018The article describes a special time-interval balancing in multi-processor scheduling of composite modular jobs. This scheduling problem is close to just-in-time planning approach. First, brief literature surveys are presented on just-in-time scheduling ... More

Multiple People Tracking Using Hierarchical Deep Tracklet Re-identificationNov 09 2018Nov 17 2018The task of multiple people tracking in monocular videos is challenging because of the numerous difficulties involved: occlusions, varying environments, crowded scenes, camera parameters and motion. In the tracking-by-detection paradigm, most approaches ... More

Deterministic and stochastic inexact regularization algorithms for nonconvex optimization with optimal complexityNov 09 2018Nov 12 2018A regularization algorithm using inexact function values and inexact derivatives is proposed and its evaluation complexity analyzed. This algorithm is applicable to unconstrained problems and to problems with inexpensive constraints (that is constraints ... More

Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex OptimizationNov 09 2018Apr 19 2019A regularization algorithm using inexact function values and inexact derivatives is proposed and its evaluation complexity analyzed. This algorithm is applicable to unconstrained problems and to problems with inexpensive constraints (that is constraints ... More

Deep BV: A Fully Automated System for Brain Ventricle Localization and Segmentation in 3D Ultrasound Images of Embryonic MiceNov 05 2018Volumetric analysis of brain ventricle (BV) structure is a key tool in the study of central nervous system development in embryonic mice. High-frequency ultrasound (HFU) is the only non-invasive, real-time modality available for rapid volumetric imaging ... More

Sharp worst-case evaluation complexity bounds for arbitrary-order nonconvex optimization with inexpensive constraintsNov 03 2018We provide sharp worst-case evaluation complexity bounds for nonconvex minimization problems with general inexpensive constraints, i.e.\ problems where the cost of evaluating/enforcing of the (possibly nonconvex or even disconnected) constraints, if any, ... More

CMI: An Online Multi-objective Genetic Autoscaler for Scientific and Engineering Workflows in Cloud Infrastructures with Unreliable Virtual MachinesNov 02 2018Cloud Computing is becoming the leading paradigm for executing scientific and engineering workflows. The large-scale nature of the experiments they model and their variable workloads make clouds the ideal execution environment due to prompt and elastic ... More

Referenceless Performance Evaluation of Audio Source Separation using Deep Neural NetworksNov 01 2018Current performance evaluation for audio source separation depends on comparing the processed or separated signals with reference signals. Therefore, common performance evaluation toolkits are not applicable to real-world situations where the ground truth ... More

Regularization Effect of Fast Gradient Sign Method and its GeneralizationOct 27 2018Oct 30 2018Fast Gradient Sign Method (FGSM) is a popular method to generate adversarial examples that make neural network models robust against perturbations. Despite its empirical success, its theoretical property is not well understood. This paper develops theory ... More

Informative Features for Model ComparisonOct 27 2018Given two candidate models, and a set of target observations, we address the problem of measuring the relative goodness of fit of the two models. We propose two new statistical tests which are nonparametric, computationally efficient (runtime complexity ... More

From the EM Algorithm to the CM-EM Algorithm for Global Convergence of Mixture ModelsOct 26 2018The Expectation-Maximization (EM) algorithm for mixture models often results in slow or invalid convergence. The popular convergence proof affirms that the likelihood increases with Q; Q is increasing in the M -step and non-decreasing in the E-step. The ... More

A minimax near-optimal algorithm for adaptive rejection samplingOct 22 2018Rejection Sampling is a fundamental Monte-Carlo method. It is used to sample from distributions admitting a probability density function which can be evaluated exactly at any given point, albeit at a high computational cost. However, without proper tuning, ... More

An $O(1/\varepsilon)$-Iteration Triangle Algorithm for A Convex Hull MembershipOct 17 2018A fundamental problem in linear programming, machine learning, and computational geometry is the {\it Convex Hull Membership} (CHM): Given a point $p$ and a subset $S$ of $n$ points in $\mathbb{R}^m$, is $p \in conv(S)$? The {\it Triangle Algorithm} (TA) ... More

Spherical Triangle Algorithm: A Fast Oracle for Convex Hull Membership QueriesOct 17 2018Apr 05 2019The it Convex Hull Membership(CHM) problem is: Given a point $p$ and a subset $S$ of $n$ points in $\mathbb{R}^m$, is $p \in conv(S)$? CHM is not only a fundamental problem in Linear Programming, Computational Geometry, Machine Learning and Statistics, ... More

On Kernel Derivative Approximation with Random Fourier FeaturesOct 11 2018Feb 09 2019Random Fourier features (RFF) represent one of the most popular and wide-spread techniques in machine learning to scale up kernel algorithms. Despite the numerous successful applications of RFFs, unfortunately, quite little is understood theoretically ... More

On the Properties of Simulation-based Estimators in High DimensionsOct 10 2018Oct 11 2018Considering the increasing size of available data, the need for statistical methods that control the finite sample bias is growing. This is mainly due to the frequent settings where the number of variables is large and allowed to increase with the sample ... More

A Practical Approach to Sizing Neural NetworksOct 04 2018Memorization is worst-case generalization. Based on MacKay's information theoretic model of supervised machine learning, this article discusses how to practically estimate the maximum size of a neural network given a training data set. First, we present ... More

Disrupting the Coming Robot Stampedes: Designing Resilient Information EcologiesOct 02 2018Nov 26 2018Machines are designed to communicate widely and efficiently. Humans, less so. We evolved social structures that function best as small subgroups interacting within larger populations. Technology changes this dynamic, by allowing all individuals to be ... More

Non-Line-of-Sight Reconstruction using Efficient Transient RenderingSep 21 2018Being able to see beyond the direct line of sight is an intriguing prospective and could benefit a wide variety of important applications. Recent work has demonstrated that time-resolved measurements of indirect diffuse light contain valuable information ... More

Poisoning Attacks to Graph-Based Recommender SystemsSep 11 2018Recommender system is an important component of many web services to help users locate items that match their interests. Several studies showed that recommender systems are vulnerable to poisoning attacks, in which an attacker injects fake data to a given ... More

Latent Molecular Optimization for Targeted Therapeutic DesignSep 05 2018We devise an approach for targeted molecular design, a problem of interest in computational drug discovery: given a target protein site, we wish to generate a chemical with both high binding affinity to the target and satisfactory pharmacological properties. ... More

From Bayesian Inference to Logical Bayesian Inference: A New Mathematical Frame for Semantic Communication and Machine LearningSep 03 2018Bayesian Inference (BI) uses the Bayes' posterior whereas Logical Bayesian Inference (LBI) uses the truth function or membership function as the inference tool. LBI was proposed because BI was not compatible with the classical Bayes' prediction and didn't ... More

AMoDSim: An Efficient and Modular Simulation Framework for Autonomous Mobility on DemandAug 14 2018Nov 06 2018Urban transportation of next decade is expected to be disrupted by Autonomous Mobility on Demand (AMoD): AMoD providers will collect ride requests from users and will dispatch a fleet of autonomous vehicles to satisfy requests in the most efficient way. ... More

Bringing Together Dynamic Geometry Software and the Graphics Processing UnitAug 14 2018We equip dynamic geometry software (DGS) with a user-friendly method that enables massively parallel calculations on the graphics processing unit (GPU). This interplay of DGS and GPU opens up various applications in education and mathematical research. ... More

Xcos on Web as a promising learning tool for Bachelor's of Electromechanics modeling of technical objectsAug 09 2018Research goals: to identify the perspective learning simulation tool for Bachelors of Electromechanics. Research objectives: to prove the feasibility of using the simulation system Xcos on Web as a tool of forming of future Bachelors of Electromechanics ... More

Simulation using random numbersAug 03 2018This article is devoted to methods of construction and study of stochastic models based on Monte Carlo method. A model of Brownian motion, the construction and processing which brings to a world of random numbers and mathematical statistics, promotes ... More

Network-Coding Approach for Information-Centric NetworkingAug 01 2018Aug 09 2018The current internet architecture is inefficient in fulfilling the demands of newly emerging internet applications. To address this issue, several over-the-top (OTT) application-level solutions have been employed, making the overall architecture very ... More

Gaussian Process Landmarking for Three-Dimensional Geometric MorphometricsJul 31 2018Jan 08 2019We demonstrate applications of the Gaussian process-based landmarking algorithm proposed in [T. Gao, S.Z. Kovalsky, and I. Daubechies, SIAM Journal on Mathematics of Data Science (2019)] to geometric morphometrics, a branch of evolutionary biology centered ... More

Competence of bachelor in electromechanics in simulationJul 27 2018The article is devoted to communication competence in modeling with other competences of Bachelor in Electromechanics, its structure and the contribution of components in the formation of competence. The approaches to defining competence of bachelor-electrician ... More

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard ModelJul 20 2018Sep 01 2018We present a novel framework that enables efficient probabilistic inference in large-scale scientific models by allowing the execution of existing domain-specific simulators as probabilistic programs, resulting in highly interpretable posterior inference. ... More

PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learningJul 20 2018Using a deep neural network, we demonstrate a digital staining technique, which we term PhaseStain, to transform quantitative phase images (QPI) of labelfree tissue sections into images that are equivalent to brightfield microscopy images of the same ... More

Uncertainty quantification for an optical grating coupler with an adjoint-based Leja adaptive collocation methodJul 19 2018This paper addresses uncertainties arising in the nano-scale fabrication of optical devices. The stochastic collocation method is used to propagate uncertainties in material and geometry to the scattering parameters of the system. A dimension-adaptive ... More

A Discriminative Approach to Bayesian Filtering with Applications to Human Neural DecodingJul 17 2018Given a stationary state-space model that relates a sequence of hidden states and corresponding measurements or observations, Bayesian filtering provides a principled statistical framework for inferring the posterior distribution of the current state ... More

The Cloud Technologies and Augmented Reality: the Prospects of UseJul 05 2018Dec 03 2018The article discusses the prospects of the augmented reality using as a component of a cloud-based environment. The research goals are the next: to explore the possibility of the augmented reality using with the involvement of the cloud-based environment ... More

Design and optimisation of an efficient HDF5 I/O kernel for massive parallel fluid flow simulationsJul 03 2018More and more massive parallel codes running on several hundreds of thousands of cores enter the computational science and engineering domain, allowing high-fidelity computations on up to trillions of unknowns for very detailed analyses of the underlying ... More

CoCalc as a Learning Tool for Neural Network Simulation in the Special Course "Foundations of Mathematic Informatics"Jul 02 2018The role of neural network modeling in the learning content of the special course "Foundations of Mathematical Informatics" was discussed. The course was developed for the students of technical universities - future IT-specialists and directed to breaking ... More

A high-performance interactive computing framework for engineering applicationsJul 02 2018To harness the potential of advanced computing technologies, efficient (real time) analysis of large amounts of data is as essential as are front-line simulations. In order to optimise this process, experts need to be supported by appropriate tools that ... More

Computer Simulation of Neural Networks Using Spreadsheets: The Dawn of the Age of CamelotJun 29 2018Dec 01 2018The article substantiates the necessity to develop training methods of computer simulation of neural networks in the spreadsheet environment. The systematic review of their application to simulating artificial neural networks is performed. The authors ... More

Towards automatic initialization of registration algorithms using simulated endoscopy imagesJun 28 2018Registering images from different modalities is an active area of research in computer aided medical interventions. Several registration algorithms have been developed, many of which achieve high accuracy. However, these results are dependent on many ... More

Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture DataJun 24 2018Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments. Afterwards, additional ... More

Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and ControlJun 21 2018This paper introduces a new generative deep learning network for human motion synthesis and control. Our key idea is to combine recurrent neural networks (RNNs) and adversarial training for human motion modeling. We first describe an efficient method ... More

Coupled Fluid Density and Motion from Single ViewsJun 18 2018We present a novel method to reconstruct a fluid's 3D density and motion based on just a single sequence of images. This is rendered possible by using powerful physical priors for this strongly under-determined problem. More specifically, we propose a ... More

Homonym Detection in Curated Bibliographies: Learning from dblp's Experience (full version)Jun 15 2018Identifying (and fixing) homonymous and synonymous author profiles is one of the major tasks of curating personalized bibliographic metadata repositories like the dblp computer science bibliography. In this paper, we present and evaluate a machine learning ... More

Data Synthesis based on Generative Adversarial NetworksJun 09 2018Jul 02 2018Privacy is an important concern for our society where sharing data with partners or releasing data to the public is a frequent occurrence. Some of the techniques that are being used to achieve privacy are to remove identifiers, alter quasi-identifiers, ... More

q-Space Novelty Detection with Variational AutoencodersJun 08 2018Oct 25 2018In machine learning, novelty detection is the task of identifying novel unseen data. During training, only samples from the normal class are available. Test samples are classified as normal or abnormal by assignment of a novelty score. Here we propose ... More

Grouped Gaussian Processes for Solar Power PredictionJun 07 2018Dec 04 2018We consider multi-task regression models where the observations are assumed to be a linear combination of several latent node functions and weight functions, which are both drawn from Gaussian process priors. Driven by the problem of developing scalable ... More

Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job PredictionJun 06 2018The 2017 ASSISTments Data Mining competition aims to use data from a longitudinal study for predicting a brand-new outcome of students which had never been studied before by the educational data mining research community. Specifically, it facilitates ... More

Addressing Two Problems in Deep Knowledge Tracing via Prediction-Consistent RegularizationJun 06 2018Knowledge tracing is one of the key research areas for empowering personalized education. It is a task to model students' mastery level of a knowledge component (KC) based on their historical learning trajectories. In recent years, a recurrent neural ... More

Deep Bayesian regression modelsJun 06 2018Jun 07 2018Regression models are used for inference and prediction in a wide range of applications providing a powerful scientific tool for researchers and analysts from different fields. In many research fields the amount of available data as well as the number ... More

Path Throughput Importance WeightsJun 04 2018Sep 06 2018Many Monte Carlo light transport simulations use multiple importance sampling (MIS) to weight between different path sampling strategies. We propose to use the path throughput to compute the MIS weights instead of the commonly used probability density ... More

Holographic Neural ArchitecturesJun 04 2018Representation learning is at the heart of what makes deep learning effective. In this work, we introduce a new framework for representation learning that we call "Holographic Neural Architectures" (HNAs). In the same way that an observer can experience ... More

Optimal Clustering under UncertaintyJun 02 2018Classical clustering algorithms typically either lack an underlying probability framework to make them predictive or focus on parameter estimation rather than defining and minimizing a notion of error. Recent work addresses these issues by developing ... More

Bayesian Learning with Wasserstein BarycentersMay 28 2018Dec 27 2018We introduce a novel paradigm for Bayesian learning based on optimal transport theory. Namely, we propose to use the Wasserstein barycenter of the posterior law on models as a predictive posterior, thus introducing an alternative to classical choices ... More

Toward a Thinking Microscope: Deep Learning in Optical Microscopy and Image ReconstructionMay 23 2018We discuss recently emerging applications of the state-of-art deep learning methods on optical microscopy and microscopic image reconstruction, which enable new transformations among different modes and modalities of microscopic imaging, driven entirely ... More

Non-parametric Structural Change Detection in Multivariate SystemsMay 22 2018Structural change detection problems are often encountered in analytics and econometrics, where the performance of a model can be significantly affected by unforeseen changes in the underlying relationships. Although these problems have a comparatively ... More

A Compositional Approach to Network AlgorithmsMay 19 2018We present elements of a typing theory for flow networks, where "types", "typings", and "type inference" are formulated in terms of familiar notions from polyhedral analysis and convex optimization. Based on this typing theory, we develop an alternative ... More

Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworksMay 17 2018We conduct an extensive empirical study on short-term electricity price forecasting (EPF) to address the long-standing question if the optimal model structure for EPF is univariate or multivariate. We provide evidence that despite a minor edge in predictive ... More

Intracranial Error Detection via Deep LearningMay 04 2018Nov 02 2018Deep learning techniques have revolutionized the field of machine learning and were recently successfully applied to various classification problems in noninvasive electroencephalography (EEG). However, these methods were so far only rarely evaluated ... More

Semantic Channel and Shannon's Channel Mutually Match for Multi-Label ClassificationMay 02 2018A group of transition probability functions form a Shannon's channel whereas a group of truth functions form a semantic channel. Label learning is to let semantic channels match Shannon's channels and label selection is to let Shannon's channels match ... More

Modelling Bitcoin in AgdaApr 17 2018We present two models of the block chain of Bitcoin in the interactive theorem prover Agda. The first one is based on a simple model of bank accounts, while having transactions with multiple inputs and outputs. The second model models transactions, which ... More

Mitigating Docker Security IssuesApr 13 2018It is very easy to run applications in Docker. Docker offers an ecosystem that offers a platform for application packaging, distributing and managing within containers. However, Docker platform is yet not matured. Presently, Docker is less secured as ... More

Experimental similarity assessment for a collection of fragmented artifactsApr 11 2018In the Visual Heritage domain, search engines are expected to support archaeologists and curators to address cross-correlation and searching across multiple collections. Archaeological excavations return artifacts that often are damaged with parts that ... More

Edge-based LBP description of surfaces with colorimetric patternsApr 11 2018In this paper we target the problem of the retrieval of colour patterns over surfaces. We generalize to surface tessellations the well known Local Binary Pattern (LBP) descriptor for images. The key concept of the LBP is to code the variability of the ... More

Learning tensors from partial binary measurementsMar 31 2018In this paper we generalize the 1-bit matrix completion problem to higher order tensors. We prove that when $r=O(1)$ a bounded rank-$r$, order-$d$ tensor $T$ in $\mathbb{R}^{N} \times \mathbb{R}^{N} \times \cdots \times \mathbb{R}^{N}$ can be estimated ... More