October 19, 2019

3031 words 15 mins read

Paper Group ANR 286

Binary Weighted Memristive Analog Deep Neural Network for Near-Sensor Edge Processing. Learning State Representations in Complex Systems with Multimodal Data. Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach. Machine Learning Enabled Computational Screening of Inorganic Solid Elect …

Binary Weighted Memristive Analog Deep Neural Network for Near-Sensor Edge Processing


Title	Binary Weighted Memristive Analog Deep Neural Network for Near-Sensor Edge Processing
Authors	Olga Krestinskaya, Alex Pappachen James
Abstract	The memristive crossbar aims to implement analog weighted neural network, however, the realistic implementation of such crossbar arrays is not possible due to limited switching states of memristive devices. In this work, we propose the design of an analog deep neural network with binary weight update through backpropagation algorithm using binary state memristive devices. We show that such networks can be successfully used for image processing task and has the advantage of lower power consumption and small on-chip area in comparison with digital counterparts. The proposed network was benchmarked for MNIST handwritten digits recognition achieving an accuracy of approximately 90%.
Tasks
Published	2018-08-02
URL	http://arxiv.org/abs/1808.00737v1
PDF	http://arxiv.org/pdf/1808.00737v1.pdf
PWC	https://paperswithcode.com/paper/binary-weighted-memristive-analog-deep-neural
Repo
Framework

Learning State Representations in Complex Systems with Multimodal Data


Title	Learning State Representations in Complex Systems with Multimodal Data
Authors	Pavel Solovev, Vladimir Aliev, Pavel Ostyakov, Gleb Sterkin, Elizaveta Logacheva, Stepan Troeshestov, Roman Suvorov, Anton Mashikhin, Oleg Khomenko, Sergey I. Nikolenko
Abstract	Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on these latent representations, but the field still lacks a large-scale standard dataset for unified comparison. In this work, we present a large-scale dataset and evaluation framework for representation learning for the complex task of landing an airplane. We implement and compare several approaches to representation learning on this dataset in terms of the quality of simple supervised learning tasks and disentanglement scores. The resulting representations can be used for further tasks such as anomaly detection, optimal control, model-based reinforcement learning, and other applications.
Tasks	Anomaly Detection, Representation Learning
Published	2018-11-27
URL	http://arxiv.org/abs/1811.11067v3
PDF	http://arxiv.org/pdf/1811.11067v3.pdf
PWC	https://paperswithcode.com/paper/learning-state-representations-in-complex
Repo
Framework

Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach


Title	Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach
Authors	Theodora S. Brisimi, Tingting Xu, Taiyao Wang, Wuyang Dai, William G. Adams, Ioannis Ch. Paschalidis
Abstract	Urban living in modern large cities has significant adverse effects on health, increasing the risk of several chronic diseases. We focus on the two leading clusters of chronic disease, heart disease and diabetes, and develop data-driven methods to predict hospitalizations due to these conditions. We base these predictions on the patients’ medical history, recent and more distant, as described in their Electronic Health Records (EHR). We formulate the prediction problem as a binary classification problem and consider a variety of machine learning methods, including kernelized and sparse Support Vector Machines (SVM), sparse logistic regression, and random forests. To strike a balance between accuracy and interpretability of the prediction, which is important in a medical setting, we propose two novel methods: K-LRT, a likelihood ratio test-based method, and a Joint Clustering and Classification (JCC) method which identifies hidden patient clusters and adapts classifiers to each cluster. We develop theoretical out-of-sample guarantees for the latter method. We validate our algorithms on large datasets from the Boston Medical Center, the largest safety-net hospital system in New England.
Tasks
Published	2018-01-03
URL	http://arxiv.org/abs/1801.01204v1
PDF	http://arxiv.org/pdf/1801.01204v1.pdf
PWC	https://paperswithcode.com/paper/predicting-chronic-disease-hospitalizations
Repo
Framework

Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Dendrite Suppression with Li Metal Anode


Title	Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Dendrite Suppression with Li Metal Anode
Authors	Zeeshan Ahmad, Tian Xie, Chinmay Maheshwari, Jeffrey C. Grossman, Venkatasubramanian Viswanathan
Abstract	Next generation batteries based on lithium (Li) metal anodes have been plagued by the dendritic electrodeposition of Li metal on the anode during cycling, resulting in short circuit and capacity loss. Suppression of dendritic growth through the use of solid electrolytes has emerged as one of the most promising strategies for enabling the use of Li metal anodes. We perform a computational screening of over 12,000 inorganic solids based on their ability to suppress dendrite initiation in contact with Li metal anode. Properties for mechanically isotropic and anisotropic interfaces that can be used in stability criteria for determining the propensity of dendrite initiation are usually obtained from computationally expensive first-principles methods. In order to obtain a large dataset for screening, we use machine learning models to predict the mechanical properties of several new solid electrolytes. We train a convolutional neural network on the shear and bulk moduli purely on structural features of the material. We use AdaBoost, Lasso and Bayesian ridge regression to train the elastic constants, where the choice of the model depended on the size of the training data and the noise that it can handle. Our models give us direct interpretability by revealing the dominant structural features affecting the elastic constants. The stiffness is found to increase with a decrease in volume per atom, increase in minimum anion-anion separation, and increase in sublattice (all but Li) packing fraction. Cross-validation/test performance suggests our models generalize well. We predict over 20 mechanically anisotropic interfaces between Li metal and 6 solid electrolytes which can be used to suppress dendrite growth. Our screened candidates are generally soft and highly anisotropic, and present opportunities for simultaneously obtaining dendrite suppression and high ionic conductivity in solid electrolytes.
Tasks
Published	2018-04-12
URL	https://arxiv.org/abs/1804.04651v1
PDF	https://arxiv.org/pdf/1804.04651v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-enabled-computational
Repo
Framework

Analysis of Thompson Sampling for Graphical Bandits Without the Graphs


Title	Analysis of Thompson Sampling for Graphical Bandits Without the Graphs
Authors	Fang Liu, Zizhan Zheng, Ness Shroff
Abstract	We study multi-armed bandit problems with graph feedback, in which the decision maker is allowed to observe the neighboring actions of the chosen action, in a setting where the graph may vary over time and is never fully revealed to the decision maker. We show that when the feedback graphs are undirected, the original Thompson Sampling achieves the optimal (within logarithmic factors) regret $\tilde{O}\left(\sqrt{\beta_0(G)T}\right)$ over time horizon $T$, where $\beta_0(G)$ is the average independence number of the latent graphs. To the best of our knowledge, this is the first result showing that the original Thompson Sampling is optimal for graphical bandits in the undirected setting. A slightly weaker regret bound of Thompson Sampling in the directed setting is also presented. To fill this gap, we propose a variant of Thompson Sampling, that attains the optimal regret in the directed setting within a logarithmic factor. Both algorithms can be implemented efficiently and do not require the knowledge of the feedback graphs at any time.
Tasks
Published	2018-05-23
URL	http://arxiv.org/abs/1805.08930v1
PDF	http://arxiv.org/pdf/1805.08930v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-thompson-sampling-for-graphical
Repo
Framework

A Novel Large-scale Ordinal Regression Model


Title	A Novel Large-scale Ordinal Regression Model
Authors	Yong Shi, Huadong Wang, Xin Shen, Lingfeng Niu
Abstract	Ordinal regression (OR) is a special multiclass classification problem where an order relation exists among the labels. Recent years, people share their opinions and sentimental judgments conveniently with social networks and E-Commerce so that plentiful large-scale OR problems arise. However, few studies have focused on this kind of problems. Nonparallel Support Vector Ordinal Regression (NPSVOR) is a SVM-based OR model, which learns a hyperplane for each rank by solving a series of independent sub-optimization problems and then ensembles those learned hyperplanes to predict. The previous studies are focused on its nonlinear case and got a competitive testing performance, but its training is time consuming, particularly for large-scale data. In this paper, we consider NPSVOR’s linear case and design an efficient training method based on the dual coordinate descent method (DCD). To utilize the order information among labels in prediction, a new prediction function is also proposed. Extensive contrast experiments on the text OR datasets indicate that the carefully implemented DCD is very suitable for training large data.
Tasks
Published	2018-12-19
URL	http://arxiv.org/abs/1812.08237v1
PDF	http://arxiv.org/pdf/1812.08237v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-large-scale-ordinal-regression-model
Repo
Framework

Multi-Exposure Image Fusion Based on Exposure Compensation


Title	Multi-Exposure Image Fusion Based on Exposure Compensation
Authors	Yuma Kinoshita, Taichi Yoshida, Sayaka Shiota, Hitoshi Kiya
Abstract	This paper proposes a novel multi-exposure image fusion method based on exposure compensation. Multi-exposure image fusion is a method to produce images without color saturation regions, by using photos with different exposures. However, in conventional works, it is unclear how to determine appropriate exposure values, and moreover, it is difficult to set appropriate exposure values at the time of photographing due to time constraints. In the proposed method, the luminance of the input multi-exposure images is adjusted on the basis of the relationship between exposure values and pixel values, where the relationship is obtained by assuming that a digital camera has a linear response function. The use of a local contrast enhancement method is also considered to improve input multi-exposure images. The compensated images are finally combined by one of existing multi-exposure image fusion methods. In some experiments, the effectiveness of the proposed method are evaluated in terms of the tone mapped image quality index, statistical naturalness, and discrete entropy, by comparing the proposed one with conventional ones.
Tasks
Published	2018-06-23
URL	http://arxiv.org/abs/1806.09607v1
PDF	http://arxiv.org/pdf/1806.09607v1.pdf
PWC	https://paperswithcode.com/paper/multi-exposure-image-fusion-based-on-exposure
Repo
Framework

Arithmetic Word Problem Solver using Frame Identification


Title	Arithmetic Word Problem Solver using Frame Identification
Authors	Pruthwik Mishra, Litton J Kurisinkel, Dipti Misra Sharma
Abstract	Automatic Word problem solving has always posed a great challenge for the NLP community. Usually a word problem is a narrative comprising of a few sentences and a question is asked about a quantity referred in the sentences. Solving word problem involves reasoning across sentences, identification of operations, their order, relevant quantities and discarding irrelevant quantities. In this paper, we present a novel approach for automatic arithmetic word problem solving. Our approach starts with frame identification. Each frame can either be classified as a state or an action frame. The frame identification is dependent on the verb in a sentence. Every frame is unique and is identified by its slots. The slots are filled using dependency parsed output of a sentence. The slots are entity holder, entity, quantity of the entity, recipient, additional information like place, time. The slots and frames helps to identify the type of question asked and the entity referred. Action frames act on state frame(s) which causes a change in quantities of the state frames. The frames are then used to build a graph where any change in quantities can be propagated to the neighboring nodes. Most of the current solvers can only answer questions related to the quantity, while our system can answer different kinds of questions like `who',` what’ other than the quantity related questions `how many’. There are three major contributions of this paper. 1. Frame Annotated Corpus (with a frame annotation tool) 2. Frame Identification Module 3. A new easily understandable Framework for word problem solving \|
Tasks
Published	2018-08-09
URL	http://arxiv.org/abs/1808.03028v1
PDF	http://arxiv.org/pdf/1808.03028v1.pdf
PWC	https://paperswithcode.com/paper/arithmetic-word-problem-solver-using-frame
Repo
Framework

A Symmetric Keyring Encryption Scheme for Biometric Cryptosystems


Title	A Symmetric Keyring Encryption Scheme for Biometric Cryptosystems
Authors	Yen-Lung Lai, Jung-Yeon Hwang, Zhe Jin, Soohyong Kim, Sangrae Cho, Andrew Beng Jin Teoh
Abstract	In this paper, we propose a novel biometric cryptosystem for vectorial biometrics named symmetric keyring encryption (SKE) inspired by Rivest’s keyring model (2016). Unlike conventional biometric secret-binding primitives, such as fuzzy commitment and fuzzy vault, the proposed scheme reframes the biometric secret-binding problem as a fuzzy symmetric encryption problem with a notion called resilient vector pair. In this study, the pair resembles the encryption-decryption key pair in symmetric key cryptosystems. This notion is realized using the index of maximum hashed vectors - a special instance of the ranking-based locality-sensitive hashing function. With a simple filtering mechanism and [m,k] Shamir’s secret-sharing scheme, we show that SKE, both in theoretical and empirical evaluation, can retrieve the exact secret with overwhelming probability for a genuine input yet negligible probability for an imposter input. Though SKE can be applied to any vectorial biometrics, we adopt the fingerprint vector as a case of study in this work. The experiments have been performed under several subsets of FVC 2002, 2004, and 2006 datasets. We formalize and analyze the threat model of SKE that encloses several major security attacks.
Tasks
Published	2018-09-28
URL	http://arxiv.org/abs/1809.11045v1
PDF	http://arxiv.org/pdf/1809.11045v1.pdf
PWC	https://paperswithcode.com/paper/a-symmetric-keyring-encryption-scheme-for
Repo
Framework

PDE-constrained LDDMM via geodesic shooting and inexact Gauss-Newton-Krylov optimization using the incremental adjoint Jacobi equations


Title	PDE-constrained LDDMM via geodesic shooting and inexact Gauss-Newton-Krylov optimization using the incremental adjoint Jacobi equations
Authors	Monica Hernandez
Abstract	The class of non-rigid registration methods proposed in the framework of PDE-constrained Large Deformation Diffeomorphic Metric Mapping is a particularly interesting family of physically meaningful diffeomorphic registration methods. Inexact Newton-Krylov optimization has shown an excellent numerical accuracy and an extraordinarily fast convergence rate in this framework. However, the Galerkin representation of the non-stationary velocity fields does not provide proper geodesic paths. In this work, we propose a method for PDE-constrained LDDMM parameterized in the space of initial velocity fields under the EPDiff equation. The derivation of the gradient and the Hessian-vector products are performed on the final velocity field and transported backward using the adjoint and the incremental adjoint Jacobi equations. This way, we avoid the complex dependence on the initial velocity field in the derivations and the computation of the adjoint equation and its incremental counterpart. The proposed method provides geodesics in the framework of PDE-constrained LDDMM, and it shows performance competitive to benchmark PDE-constrained LDDMM and EPDiff-LDDMM methods.
Tasks
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04638v1
PDF	http://arxiv.org/pdf/1807.04638v1.pdf
PWC	https://paperswithcode.com/paper/pde-constrained-lddmm-via-geodesic-shooting
Repo
Framework

Consequences and Factors of Stylistic Differences in Human-Robot Dialogue


Title	Consequences and Factors of Stylistic Differences in Human-Robot Dialogue
Authors	Stephanie M. Lukin, Kimberly A. Pollard, Claire Bonial, Matthew Marge, Cassidy Henry, Ron Arstein, David Traum, Clare R. Voss
Abstract	This paper identifies stylistic differences in instruction-giving observed in a corpus of human-robot dialogue. Differences in verbosity and structure (i.e., single-intent vs. multi-intent instructions) arose naturally without restrictions or prior guidance on how users should speak with the robot. Different styles were found to produce different rates of miscommunication, and correlations were found between style differences and individual user variation, trust, and interaction experience with the robot. Understanding potential consequences and factors that influence style can inform design of dialogue systems that are robust to natural variation from human users.
Tasks
Published	2018-07-21
URL	http://arxiv.org/abs/1807.08076v1
PDF	http://arxiv.org/pdf/1807.08076v1.pdf
PWC	https://paperswithcode.com/paper/consequences-and-factors-of-stylistic
Repo
Framework

DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth


Title	DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth
Authors	Jameel Malik, Ahmed Elhayek, Fabrizio Nunnari, Kiran Varanasi, Kiarash Tamaddon, Alexis Heloir, Didier Stricker
Abstract	Articulated hand pose and shape estimation is an important problem for vision-based applications such as augmented reality and animation. In contrast to the existing methods which optimize only for joint positions, we propose a fully supervised deep network which learns to jointly estimate a full 3D hand mesh representation and pose from a single depth image. To this end, a CNN architecture is employed to estimate parametric representations i.e. hand pose, bone scales and complex shape parameters. Then, a novel hand pose and shape layer, embedded inside our deep framework, produces 3D joint positions and hand mesh. Lack of sufficient training data with varying hand shapes limits the generalized performance of learning based methods. Also, manually annotating real data is suboptimal. Therefore, we present SynHand5M: a million-scale synthetic dataset with accurate joint annotations, segmentation masks and mesh files of depth maps. Among model based learning (hybrid) methods, we show improved results on our dataset and two of the public benchmarks i.e. NYU and ICVL. Also, by employing a joint training strategy with real and synthetic data, we recover 3D hand mesh and pose from real images in 3.7ms.
Tasks
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09208v1
PDF	http://arxiv.org/pdf/1808.09208v1.pdf
PWC	https://paperswithcode.com/paper/deephps-end-to-end-estimation-of-3d-hand-pose
Repo
Framework

Deep Lidar CNN to Understand the Dynamics of Moving Vehicles


Title	Deep Lidar CNN to Understand the Dynamics of Moving Vehicles
Authors	Victor Vaquero, Alberto Sanfeliu, Francesc Moreno-Noguer
Abstract	Perception technologies in Autonomous Driving are experiencing their golden age due to the advances in Deep Learning. Yet, most of these systems rely on the semantically rich information of RGB images. Deep Learning solutions applied to the data of other sensors typically mounted on autonomous cars (e.g. lidars or radars) are not explored much. In this paper we propose a novel solution to understand the dynamics of moving vehicles of the scene from only lidar information. The main challenge of this problem stems from the fact that we need to disambiguate the proprio-motion of the ‘observer’ vehicle from that of the external ‘observed’ vehicles. For this purpose, we devise a CNN architecture which at testing time is fed with pairs of consecutive lidar scans. However, in order to properly learn the parameters of this network, during training we introduce a series of so-called pretext tasks which also leverage on image data. These tasks include semantic information about vehicleness and a novel lidar-flow feature which combines standard image-based optical flow with lidar scans. We obtain very promising results and show that including distilled image information only during training, allows improving the inference results of the network at test time, even when image data is no longer used.
Tasks	Autonomous Driving, Optical Flow Estimation
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09526v2
PDF	http://arxiv.org/pdf/1808.09526v2.pdf
PWC	https://paperswithcode.com/paper/deep-lidar-cnn-to-understand-the-dynamics-of
Repo
Framework

Computational speedups using small quantum devices


Title	Computational speedups using small quantum devices
Authors	Vedran Dunjko, Yimin Ge, J. Ignacio Cirac
Abstract	Suppose we have a small quantum computer with only M qubits. Can such a device genuinely speed up certain algorithms, even when the problem size is much larger than M? Here we answer this question to the affirmative. We present a hybrid quantum-classical algorithm to solve 3SAT problems involving n»M variables that significantly speeds up its fully classical counterpart. This question may be relevant in view of the current quest to build small quantum computers.
Tasks
Published	2018-07-24
URL	http://arxiv.org/abs/1807.08970v2
PDF	http://arxiv.org/pdf/1807.08970v2.pdf
PWC	https://paperswithcode.com/paper/computational-speedups-using-small-quantum
Repo
Framework

Human-Competitive Awards 2018


Title	Human-Competitive Awards 2018
Authors	W. B. Langdon
Abstract	Report on Humies competition at GECCO 2018 in Japan
Tasks
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09416v1
PDF	http://arxiv.org/pdf/1810.09416v1.pdf
PWC	https://paperswithcode.com/paper/human-competitive-awards-2018
Repo
Framework