May 7, 2019

3426 words 17 mins read

Paper Group ANR 16

Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model. Delta Networks for Optimized Recurrent Network Computation. Variational Inference via $χ$-Upper Bound Minimization. Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation. Learning to Translate for Multilingual Question Answ …


Title	Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model
Authors	Zhen Xu, Wen Dong, Sargur Srihari
Abstract	Social dynamics is concerned primarily with interactions among individuals and the resulting group behaviors, modeling the temporal evolution of social systems via the interactions of individuals within these systems. In particular, the availability of large-scale data from social networks and sensor networks offers an unprecedented opportunity to predict state-changing events at the individual level. Examples of such events include disease transmission, opinion transition in elections, and rumor propagation. Unlike previous research focusing on the collective effects of social systems, this study makes efficient inferences at the individual level. In order to cope with dynamic interactions among a large number of individuals, we introduce the stochastic kinetic model to capture adaptive transition probabilities and propose an efficient variational inference algorithm the complexity of which grows linearly — rather than exponentially — with the number of individuals. To validate this method, we have performed epidemic-dynamics experiments on wireless sensor network data collected from more than ten thousand people over three years. The proposed algorithm was used to track disease transmission and predict the probability of infection for each individual. Our results demonstrate that this method is more efficient than sampling while nonetheless achieving high accuracy.
Tasks
Published	2016-11-07
URL	http://arxiv.org/abs/1611.02181v1
PDF	http://arxiv.org/pdf/1611.02181v1.pdf
PWC	https://paperswithcode.com/paper/using-social-dynamics-to-make-individual
Repo
Framework

Delta Networks for Optimized Recurrent Network Computation


Title	Delta Networks for Optimized Recurrent Network Computation
Authors	Daniel Neil, Jun Haeng Lee, Tobi Delbruck, Shih-Chii Liu
Abstract	Many neural networks exhibit stability in their activation patterns over time in response to inputs from sensors operating under real-world conditions. By capitalizing on this property of natural signals, we propose a Recurrent Neural Network (RNN) architecture called a delta network in which each neuron transmits its value only when the change in its activation exceeds a threshold. The execution of RNNs as delta networks is attractive because their states must be stored and fetched at every timestep, unlike in convolutional neural networks (CNNs). We show that a naive run-time delta network implementation offers modest improvements on the number of memory accesses and computes, but optimized training techniques confer higher accuracy at higher speedup. With these optimizations, we demonstrate a 9X reduction in cost with negligible loss of accuracy for the TIDIGITS audio digit recognition benchmark. Similarly, on the large Wall Street Journal speech recognition benchmark even existing networks can be greatly accelerated as delta networks, and a 5.7x improvement with negligible loss of accuracy can be obtained through training. Finally, on an end-to-end CNN trained for steering angle prediction in a driving dataset, the RNN cost can be reduced by a substantial 100X.
Tasks	Speech Recognition
Published	2016-12-16
URL	http://arxiv.org/abs/1612.05571v1
PDF	http://arxiv.org/pdf/1612.05571v1.pdf
PWC	https://paperswithcode.com/paper/delta-networks-for-optimized-recurrent
Repo
Framework

Variational Inference via $χ$-Upper Bound Minimization


Title	Variational Inference via $χ$-Upper Bound Minimization
Authors	Adji B. Dieng, Dustin Tran, Rajesh Ranganath, John Paisley, David M. Blei
Abstract	Variational inference (VI) is widely used as an efficient alternative to Markov chain Monte Carlo. It posits a family of approximating distributions $q$ and finds the closest member to the exact posterior $p$. Closeness is usually measured via a divergence $D(q p)$ from $q$ to $p$. While successful, this approach also has problems. Notably, it typically leads to underestimation of the posterior variance. In this paper we propose CHIVI, a black-box variational inference algorithm that minimizes $D_{\chi}(p q)$, the $\chi$-divergence from $p$ to $q$. CHIVI minimizes an upper bound of the model evidence, which we term the $\chi$ upper bound (CUBO). Minimizing the CUBO leads to improved posterior uncertainty, and it can also be used with the classical VI lower bound (ELBO) to provide a sandwich estimate of the model evidence. We study CHIVI on three models: probit regression, Gaussian process classification, and a Cox process model of basketball plays. When compared to expectation propagation and classical VI, CHIVI produces better error rates and more accurate estimates of posterior variance.
Tasks
Published	2016-11-01
URL	http://arxiv.org/abs/1611.00328v4
PDF	http://arxiv.org/pdf/1611.00328v4.pdf
PWC	https://paperswithcode.com/paper/variational-inference-via-upper-bound
Repo
Framework

Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation


Title	Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation
Authors	Weihao Gao, Sewoong Oh, Pramod Viswanath
Abstract	Estimators of information theoretic measures such as entropy and mutual information are a basic workhorse for many downstream applications in modern data science. State of the art approaches have been either geometric (nearest neighbor (NN) based) or kernel based (with a globally chosen bandwidth). In this paper, we combine both these approaches to design new estimators of entropy and mutual information that outperform state of the art methods. Our estimator uses local bandwidth choices of $k$-NN distances with a finite $k$, independent of the sample size. Such a local and data dependent choice improves performance in practice, but the bandwidth is vanishing at a fast rate, leading to a non-vanishing bias. We show that the asymptotic bias of the proposed estimator is universal; it is independent of the underlying distribution. Hence, it can be pre-computed and subtracted from the estimate. As a byproduct, we obtain a unified way of obtaining both kernel and NN estimators. The corresponding theoretical contribution relating the asymptotic geometry of nearest neighbors to order statistics is of independent mathematical interest.
Tasks
Published	2016-09-07
URL	http://arxiv.org/abs/1609.02208v1
PDF	http://arxiv.org/pdf/1609.02208v1.pdf
PWC	https://paperswithcode.com/paper/breaking-the-bandwidth-barrier-geometrical
Repo
Framework

Learning to Translate for Multilingual Question Answering


Title	Learning to Translate for Multilingual Question Answering
Authors	Ferhan Ture, Elizabeth Boschee
Abstract	In multilingual question answering, either the question needs to be translated into the document language, or vice versa. In addition to direction, there are multiple methods to perform the translation, four of which we explore in this paper: word-based, 10-best, context-based, and grammar-based. We build a feature for each combination of translation direction and method, and train a model that learns optimal feature weights. On a large forum dataset consisting of posts in English, Arabic, and Chinese, our novel learn-to-translate approach was more effective than a strong baseline (p<0.05): translating all text into English, then training a classifier based only on English (original or translated) text.
Tasks	Question Answering
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08210v1
PDF	http://arxiv.org/pdf/1609.08210v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-translate-for-multilingual
Repo
Framework

Dual Purpose Hashing


Title	Dual Purpose Hashing
Authors	Haomiao Liu, Ruiping Wang, Shiguang Shan, Xilin Chen
Abstract	Recent years have seen more and more demand for a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes. Considering the scale of modern datasets, hashing is favorable for its low complexity. However, most existing hashing methods are designed to preserve one single kind of similarity, thus improper for dealing with the different tasks simultaneously. To overcome this limitation, we propose a new hashing method, named Dual Purpose Hashing (DPH), which jointly preserves the category and attribute similarities by exploiting the Convolutional Neural Network (CNN) models to hierarchically capture the correlations between category and attributes. Since images with both category and attribute labels are scarce, our method is designed to take the abundant partially labelled images on the Internet as training inputs. With such a framework, the binary codes of new-coming images can be readily obtained by quantizing the network outputs of a binary-like layer, and the attributes can be recovered from the codes easily. Experiments on two large-scale datasets show that our dual purpose hash codes can achieve comparable or even better performance than those state-of-the-art methods specifically designed for each individual retrieval task, while being more compact than the compared methods.
Tasks	Image Retrieval
Published	2016-07-19
URL	http://arxiv.org/abs/1607.05529v1
PDF	http://arxiv.org/pdf/1607.05529v1.pdf
PWC	https://paperswithcode.com/paper/dual-purpose-hashing
Repo
Framework

CRTS: A type system for representing clinical recommendations


Title	CRTS: A type system for representing clinical recommendations
Authors	Ravi P Garg, Kalpana Raja, Siddhartha R Jonnalagadda
Abstract	Background: Clinical guidelines and recommendations are the driving wheels of the evidence-based medicine (EBM) paradigm, but these are available primarily as unstructured text and are generally highly heterogeneous in nature. This significantly reduces the dissemination and automatic application of these recommendations at the point of care. A comprehensive structured representation of these recommendations is highly beneficial in this regard. Objective: The objective of this paper to present Clinical Recommendation Type System (CRTS), a common type system that can effectively represent a clinical recommendation in a structured form. Methods: CRTS is built by analyzing 125 recommendations and 195 research articles corresponding to 6 different diseases available from UpToDate, a publicly available clinical knowledge system, and from the National Guideline Clearinghouse, a public resource for evidence-based clinical practice guidelines. Results: We show that CRTS not only covers the recommendations but also is flexible to be extended to represent information from primary literature. We also describe how our developed type system can be applied for clinical decision support, medical knowledge summarization, and citation retrieval. Conclusion: We showed that our proposed type system is precise and comprehensive in representing a large sample of recommendations available for various disorders. CRTS can now be used to build interoperable information extraction systems that automatically extract clinical recommendations and related data elements from clinical evidence resources, guidelines, systematic reviews and primary publications. Keywords: guidelines and recommendations, type system, clinical decision support, evidence-based medicine, information storage and retrieval
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01592v1
PDF	http://arxiv.org/pdf/1609.01592v1.pdf
PWC	https://paperswithcode.com/paper/crts-a-type-system-for-representing-clinical
Repo
Framework

Mixed Neural Network Approach for Temporal Sleep Stage Classification


Title	Mixed Neural Network Approach for Temporal Sleep Stage Classification
Authors	Hao Dong, Akara Supratak, Wei Pan, Chao Wu, Paul M. Matthews, Yike Guo
Abstract	This paper proposes a practical approach to addressing limitations posed by use of single active electrodes in applications for sleep stage classification. Electroencephalography (EEG)-based characterizations of sleep stage progression contribute the diagnosis and monitoring of the many pathologies of sleep. Several prior reports have explored ways of automating the analysis of sleep EEG and of reducing the complexity of the data needed for reliable discrimination of sleep stages in order to make it possible to perform sleep studies at lower cost in the home (rather than only in specialized clinical facilities). However, these reports have involved recordings from electrodes placed on the cranial vertex or occiput, which can be uncomfortable or difficult for subjects to position. Those that have utilized single EEG channels which contain less sleep information, have showed poor classification performance. We have taken advantage of Rectifier Neural Network for feature detection and Long Short-Term Memory (LSTM) network for sequential data learning to optimize classification performance with single electrode recordings. After exploring alternative electrode placements, we found a comfortable configuration of a single-channel EEG on the forehead and have shown that it can be integrated with additional electrodes for simultaneous recording of the electroocuolgram (EOG). Evaluation of data from 62 people (with 494 hours sleep) demonstrated better performance of our analytical algorithm for automated sleep classification than existing approaches using vertex or occipital electrode placements. Use of this recording configuration with neural network deconvolution promises to make clinically indicated home sleep studies practical.
Tasks	EEG
Published	2016-10-15
URL	http://arxiv.org/abs/1610.06421v3
PDF	http://arxiv.org/pdf/1610.06421v3.pdf
PWC	https://paperswithcode.com/paper/mixed-neural-network-approach-for-temporal
Repo
Framework

Stabilizing Linear Prediction Models using Autoencoder


Title	Stabilizing Linear Prediction Models using Autoencoder
Authors	Shivapratap Gopakumar, Truyen Tran, Dinh Phung, Svetha Venkatesh
Abstract	To date, the instability of prognostic predictors in a sparse high dimensional model, which hinders their clinical adoption, has received little attention. Stable prediction is often overlooked in favour of performance. Yet, stability prevails as key when adopting models in critical areas as healthcare. Our study proposes a stabilization scheme by detecting higher order feature correlations. Using a linear model as basis for prediction, we achieve feature stability by regularising latent correlation in features. Latent higher order correlation among features is modelled using an autoencoder network. Stability is enhanced by combining a recent technique that uses a feature graph, and augmenting external unlabelled data for training the autoencoder network. Our experiments are conducted on a heart failure cohort from an Australian hospital. Stability was measured using Consistency index for feature subsets and signal-to-noise ratio for model parameters. Our methods demonstrated significant improvement in feature stability and model estimation stability when compared to baselines.
Tasks
Published	2016-09-28
URL	http://arxiv.org/abs/1609.08752v1
PDF	http://arxiv.org/pdf/1609.08752v1.pdf
PWC	https://paperswithcode.com/paper/stabilizing-linear-prediction-models-using
Repo
Framework

Solving Optimization Problems by the Public Goods Game


Title	Solving Optimization Problems by the Public Goods Game
Authors	Marco Alberto Javarone
Abstract	We introduce a method based on the Public Goods Game for solving optimization tasks. In particular, we focus on the Traveling Salesman Problem, i.e. a NP-hard problem whose search space exponentially grows increasing the number of cities. The proposed method considers a population whose agents are provided with a random solution to the given problem. In doing so, agents interact by playing the Public Goods Game using the fitness of their solution as currency of the game. Notably, agents with better solutions provide higher contributions, while those with lower ones tend to imitate the solution of richer agents for increasing their fitness. Numerical simulations show that the proposed method allows to compute exact solutions, and suboptimal ones, in the considered search spaces. As result, beyond to propose a new heuristic for combinatorial optimization problems, our work aims to highlight the potentiality of evolutionary game theory beyond its current horizons.
Tasks	Combinatorial Optimization
Published	2016-04-07
URL	http://arxiv.org/abs/1604.02929v2
PDF	http://arxiv.org/pdf/1604.02929v2.pdf
PWC	https://paperswithcode.com/paper/solving-optimization-problems-by-the-public
Repo
Framework

Predicting Ambulance Demand: Challenges and Methods


Title	Predicting Ambulance Demand: Challenges and Methods
Authors	Zhengyi Zhou
Abstract	Predicting ambulance demand accurately at a fine resolution in time and space (e.g., every hour and 1 km$^2$) is critical for staff / fleet management and dynamic deployment. There are several challenges: though the dataset is typically large-scale, demand per time period and locality is almost always zero. The demand arises from complex urban geography and exhibits complex spatio-temporal patterns, both of which need to captured and exploited. To address these challenges, we propose three methods based on Gaussian mixture models, kernel density estimation, and kernel warping. These methods provide spatio-temporal predictions for Toronto and Melbourne that are significantly more accurate than the current industry practice.
Tasks	Density Estimation
Published	2016-06-16
URL	http://arxiv.org/abs/1606.05363v1
PDF	http://arxiv.org/pdf/1606.05363v1.pdf
PWC	https://paperswithcode.com/paper/predicting-ambulance-demand-challenges-and
Repo
Framework

Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation from Single and Multiple Images


Title	Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation from Single and Multiple Images
Authors	Yuan Gao, Alan L. Yuille
Abstract	Many man-made objects have intrinsic symmetries and Manhattan structure. By assuming an orthographic projection model, this paper addresses the estimation of 3D structures and camera projection using symmetry and/or Manhattan structure cues, which occur when the input is single- or multiple-image from the same category, e.g., multiple different cars. Specifically, analysis on the single image case implies that Manhattan alone is sufficient to recover the camera projection, and then the 3D structure can be reconstructed uniquely exploiting symmetry. However, Manhattan structure can be difficult to observe from a single image due to occlusion. To this end, we extend to the multiple-image case which can also exploit symmetry but does not require Manhattan axes. We propose a novel rigid structure from motion method, exploiting symmetry and using multiple images from the same category as input. Experimental results on the Pascal3D+ dataset show that our method significantly outperforms baseline methods.
Tasks
Published	2016-07-25
URL	http://arxiv.org/abs/1607.07129v3
PDF	http://arxiv.org/pdf/1607.07129v3.pdf
PWC	https://paperswithcode.com/paper/exploiting-symmetry-andor-manhattan
Repo
Framework

Dynamic Concept Composition for Zero-Example Event Detection


Title	Dynamic Concept Composition for Zero-Example Event Detection
Authors	Xiaojun Chang, Yi Yang, Guodong Long, Chengqi Zhang, Alexander G. Hauptmann
Abstract	In this paper, we focus on automatically detecting events in unconstrained videos without the use of any visual training exemplars. In principle, zero-shot learning makes it possible to train an event detection model based on the assumption that events (e.g. \emph{birthday party}) can be described by multiple mid-level semantic concepts (e.g. “blowing candle”, “birthday cake”). Towards this goal, we first pre-train a bundle of concept classifiers using data from other sources. Then we evaluate the semantic correlation of each concept \wrt the event of interest and pick up the relevant concept classifiers, which are applied on all test videos to get multiple prediction score vectors. While most existing systems combine the predictions of the concept classifiers with fixed weights, we propose to learn the optimal weights of the concept classifiers for each testing video by exploring a set of online available videos with free-form text descriptions of their content. To validate the effectiveness of the proposed approach, we have conducted extensive experiments on the latest TRECVID MEDTest 2014, MEDTest 2013 and CCV dataset. The experimental results confirm the superiority of the proposed approach.
Tasks	Zero-Shot Learning
Published	2016-01-14
URL	http://arxiv.org/abs/1601.03679v1
PDF	http://arxiv.org/pdf/1601.03679v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-concept-composition-for-zero-example
Repo
Framework

ARES: Adaptive Receding-Horizon Synthesis of Optimal Plans


Title	ARES: Adaptive Receding-Horizon Synthesis of Optimal Plans
Authors	Anna Lukina, Lukas Esterle, Christian Hirsch, Ezio Bartocci, Junxing Yang, Ashish Tiwari, Scott A. Smolka, Radu Grosu
Abstract	We introduce ARES, an efficient approximation algorithm for generating optimal plans (action sequences) that take an initial state of a Markov Decision Process (MDP) to a state whose cost is below a specified (convergence) threshold. ARES uses Particle Swarm Optimization, with adaptive sizing for both the receding horizon and the particle swarm. Inspired by Importance Splitting, the length of the horizon and the number of particles are chosen such that at least one particle reaches a next-level state, that is, a state where the cost decreases by a required delta from the previous-level state. The level relation on states and the plans constructed by ARES implicitly define a Lyapunov function and an optimal policy, respectively, both of which could be explicitly generated by applying ARES to all states of the MDP, up to some topological equivalence relation. We also assess the effectiveness of ARES by statistically evaluating its rate of success in generating optimal plans. The ARES algorithm resulted from our desire to clarify if flying in V-formation is a flocking policy that optimizes energy conservation, clear view, and velocity alignment. That is, we were interested to see if one could find optimal plans that bring a flock from an arbitrary initial state to a state exhibiting a single connected V-formation. For flocks with 7 birds, ARES is able to generate a plan that leads to a V-formation in 95% of the 8,000 random initial configurations within 63 seconds, on average. ARES can also be easily customized into a model-predictive controller (MPC) with an adaptive receding horizon and statistical guarantees of convergence. To the best of our knowledge, our adaptive-sizing approach is the first to provide convergence guarantees in receding-horizon techniques.
Tasks
Published	2016-12-21
URL	http://arxiv.org/abs/1612.07059v1
PDF	http://arxiv.org/pdf/1612.07059v1.pdf
PWC	https://paperswithcode.com/paper/ares-adaptive-receding-horizon-synthesis-of
Repo
Framework

A deep learning approach for predicting the quality of online health expert question-answering services


Title	A deep learning approach for predicting the quality of online health expert question-answering services
Authors	Ze Hu, Zhan Zhang, Qing Chen, Haiqin Yang, Decheng Zuo
Abstract	Currently, a growing number of health consumers are asking health-related questions online, at any time and from anywhere, which effectively lowers the cost of health care. The most common approach is using online health expert question-answering (HQA) services, as health consumers are more willing to trust answers from professional physicians. However, these answers can be of varying quality depending on circumstance. In addition, as the available HQA services grow, how to predict the answer quality of HQA services via machine learning becomes increasingly important and challenging. In an HQA service, answers are normally short texts, which are severely affected by the data sparsity problem. Furthermore, HQA services lack community features such as best answer and user votes. Therefore, the wisdom of the crowd is not available to rate answer quality. To address these problems, in this paper, the prediction of HQA answer quality is defined as a classification task. First, based on the characteristics of HQA services and feedback from medical experts, a standard for HQA service answer quality evaluation is defined. Next, based on the characteristics of HQA services, several novel non-textual features are proposed, including surface linguistic features and social features. Finally, a deep belief network (DBN)-based HQA answer quality prediction framework is proposed to predict the quality of answers by learning the high-level hidden semantic representation from the physicians’ answers. Our results prove that the proposed framework overcomes the problem of overly sparse textual features in short text answers and effectively identifies high-quality answers.
Tasks	Question Answering
Published	2016-12-21
URL	http://arxiv.org/abs/1612.07040v1
PDF	http://arxiv.org/pdf/1612.07040v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-approach-for-predicting-the
Repo
Framework