May 6, 2019

3111 words 15 mins read

Paper Group ANR 435

STDP-based spiking deep convolutional neural networks for object recognition. Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines. Real Time Video Analysis using Smart Phone Camera for Stroboscopic Image. Modeling community structure and topics in dynamic text networks. Depth Reconstruction and Computer-Aided Polyp Detection in Op …

STDP-based spiking deep convolutional neural networks for object recognition


Title	STDP-based spiking deep convolutional neural networks for object recognition
Authors	Saeed Reza Kheradpisheh, Mohammad Ganjtabesh, Simon J Thorpe, Timothée Masquelier
Abstract	Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in spiking neural networks (SNN) to extract visual features of low or intermediate complexity in an unsupervised manner. These studies, however, used relatively shallow architectures, and only one layer was trainable. Another line of research has demonstrated - using rate-based neural networks trained with back-propagation - that having many layers increases the recognition robustness, an approach known as deep learning. We thus designed a deep SNN, comprising several convolutional (trainable with STDP) and pooling layers. We used a temporal coding scheme where the most strongly activated neurons fire first, and less activated neurons fire later or not at all. The network was exposed to natural images. Thanks to STDP, neurons progressively learned features corresponding to prototypical patterns that were both salient and frequent. Only a few tens of examples per category were required and no label was needed. After learning, the complexity of the extracted features increased along the hierarchy, from edge detectors in the first layer to object prototypes in the last layer. Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron. More generally, the activity of a few hundreds of such neurons contained robust category information, as demonstrated using a classifier on Caltech 101, ETH-80, and MNIST databases. We also demonstrate the superiority of STDP over other unsupervised techniques such as random crops (HMAX) or auto-encoders. Taken together, our results suggest that the combination of STDP with latency coding may be a key to understanding the way that the primate visual system learns, its remarkable processing speed and its low energy consumption.
Tasks	Object Recognition
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01421v3
PDF	http://arxiv.org/pdf/1611.01421v3.pdf
PWC	https://paperswithcode.com/paper/stdp-based-spiking-deep-convolutional-neural
Repo
Framework

Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines


Title	Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
Authors	Li Huang, Lei Wang
Abstract	Despite their exceptional flexibility and popularity, the Monte Carlo methods often suffer from slow mixing times for challenging statistical physics problems. We present a general strategy to overcome this difficulty by adopting ideas and techniques from the machine learning community. We fit the unnormalized probability of the physical model to a feedforward neural network and reinterpret the architecture as a restricted Boltzmann machine. Then, exploiting its feature detection ability, we utilize the restricted Boltzmann machine for efficient Monte Carlo updates and to speed up the simulation of the original physical system. We implement these ideas for the Falicov-Kimball model and demonstrate improved acceptance ratio and autocorrelation time near the phase transition point.
Tasks
Published	2016-10-10
URL	http://arxiv.org/abs/1610.02746v2
PDF	http://arxiv.org/pdf/1610.02746v2.pdf
PWC	https://paperswithcode.com/paper/accelerate-monte-carlo-simulations-with
Repo
Framework

Real Time Video Analysis using Smart Phone Camera for Stroboscopic Image


Title	Real Time Video Analysis using Smart Phone Camera for Stroboscopic Image
Authors	Somnath Mukherjee, Soumyajit Ganguly
Abstract	Motion capturing and there by segmentation of the motion of any moving object from a sequence of continuous images or a video is not an exceptional task in computer vision area. Smart-phone camera application is an added integration for the development of such tasks and it also provides for a smooth testing. A new approach has been proposed for segmenting out the foreground moving object from the background and then masking the sequential motion with the static background which is commonly known as stroboscopic image. In this paper the whole process of the stroboscopic image construction technique has been clearly described along with some necessary constraints which is due to the traditional problem of estimating and modeling dynamic background changes. The background subtraction technique has been properly estimated here and number of sequential motion have also been calculated with the correlation between the motion of the object and its time of occurrence. This can be a very effective application that can replace the traditional stroboscopic system using high end SLR cameras, tripod stand, shutter speed control and position etc.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03217v1
PDF	http://arxiv.org/pdf/1611.03217v1.pdf
PWC	https://paperswithcode.com/paper/real-time-video-analysis-using-smart-phone
Repo
Framework

Modeling community structure and topics in dynamic text networks


Title	Modeling community structure and topics in dynamic text networks
Authors	Teague Henry, David Banks, Christine Chai, Derek Owens-Oas
Abstract	The last decade has seen great progress in both dynamic network modeling and topic modeling. This paper draws upon both areas to create a Bayesian method that allows topic discovery to inform the latent network model and the network structure to facilitate topic identification. We apply this method to the 467 top political blogs of 2012. Our results find complex community structure within this set of blogs, where community membership depends strongly upon the set of topics in which the blogger is interested.
Tasks
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05756v2
PDF	http://arxiv.org/pdf/1610.05756v2.pdf
PWC	https://paperswithcode.com/paper/modeling-community-structure-and-topics-in
Repo
Framework

Depth Reconstruction and Computer-Aided Polyp Detection in Optical Colonoscopy Video Frames


Title	Depth Reconstruction and Computer-Aided Polyp Detection in Optical Colonoscopy Video Frames
Authors	Saad Nadeem, Arie Kaufman
Abstract	We present a computer-aided detection algorithm for polyps in optical colonoscopy images. Polyps are the precursors to colon cancer. In the US alone, more than 14 million optical colonoscopies are performed every year, mostly to screen for polyps. Optical colonoscopy has been shown to have an approximately 25% polyp miss rate due to the convoluted folds and bends present in the colon. In this work, we present an automatic detection algorithm to detect these polyps in the optical colonoscopy images. We use a machine learning algorithm to infer a depth map for a given optical colonoscopy image and then use a detailed pre-built polyp profile to detect and delineate the boundaries of polyps in this given image. We have achieved the best recall of 84.0% and the best specificity value of 83.4%.
Tasks
Published	2016-09-05
URL	http://arxiv.org/abs/1609.01329v2
PDF	http://arxiv.org/pdf/1609.01329v2.pdf
PWC	https://paperswithcode.com/paper/depth-reconstruction-and-computer-aided-polyp
Repo
Framework

Data-Driven Dynamic Decision Models


Title	Data-Driven Dynamic Decision Models
Authors	John J. Nay, Jonathan M. Gilligan
Abstract	This article outlines a method for automatically generating models of dynamic decision-making that both have strong predictive power and are interpretable in human terms. This is useful for designing empirically grounded agent-based simulations and for gaining direct insight into observed dynamic processes. We use an efficient model representation and a genetic algorithm-based estimation process to generate simple approximations that explain most of the structure of complex stochastic processes. This method, implemented in C++ and R, scales well to large data sets. We apply our methods to empirical data from human subjects game experiments and international relations. We also demonstrate the method’s ability to recover known data-generating processes by simulating data with agent-based models and correctly deriving the underlying decision models for multiple agent models and degrees of stochasticity.
Tasks	Decision Making
Published	2016-03-26
URL	http://arxiv.org/abs/1603.08150v1
PDF	http://arxiv.org/pdf/1603.08150v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-dynamic-decision-models
Repo
Framework

Who’s that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images


Title	Who’s that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images
Authors	Rahaf Aljundi, Punarjay Chakravarty, Tinne Tuytelaars
Abstract	In this work, we aim at automatically labeling actors in a TV series. Rather than relying on transcripts and subtitles, as has been demonstrated in the past, we show how to achieve this goal starting from a set of example images of each of the main actors involved, collected from the Internet Movie Database (IMDB). The problem then becomes one of domain adaptation: actors’ IMDB photos are typically taken at awards ceremonies and are quite different from their appearances in TV series. In each series as well, there is considerable change in actor appearance due to makeup, lighting, ageing, etc. To bridge this gap, we propose a graph-matching based self-labelling algorithm, which we coin HSL (Hungarian Self Labeling). Further, we propose a new edge cost to be used in this context, as well as an extension that is more robust to outliers, where prototypical faces for each of the actors are selected based on a hierarchical clustering procedure. We conduct experiments with 15 episodes from 3 different TV series and demonstrate automatic annotation with an accuracy of 90% and up.
Tasks	Domain Adaptation, Graph Matching
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09162v1
PDF	http://arxiv.org/pdf/1611.09162v1.pdf
PWC	https://paperswithcode.com/paper/whos-that-actor-automatic-labelling-of-actors
Repo
Framework

Multitask Learning of Vegetation Biochemistry from Hyperspectral Data


Title	Multitask Learning of Vegetation Biochemistry from Hyperspectral Data
Authors	Utsav B. Gewali, Sildomar T. Monteiro
Abstract	Statistical models have been successful in accurately estimating the biochemical contents of vegetation from the reflectance spectra. However, their performance deteriorates when there is a scarcity of sizable amount of ground truth data for modeling the complex non-linear relationship occurring between the spectrum and the biochemical quantity. We propose a novel Gaussian process based multitask learning method for improving the prediction of a biochemical through the transfer of knowledge from the learned models for predicting related biochemicals. This method is most advantageous when there are few ground truth data for the biochemical of interest, but plenty of ground truth data for related biochemicals. The proposed multitask Gaussian process hypothesizes that the inter-relationship between the biochemical quantities is better modeled by using a combination of two or more covariance functions and inter-task correlation matrices. In the experiments, our method outperformed the current methods on two real-world datasets.
Tasks
Published	2016-10-22
URL	http://arxiv.org/abs/1610.06987v1
PDF	http://arxiv.org/pdf/1610.06987v1.pdf
PWC	https://paperswithcode.com/paper/multitask-learning-of-vegetation-biochemistry
Repo
Framework

On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems


Title	On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
Authors	Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
Abstract	The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedback as the reward signal is often unreliable and costly to collect. This problem can be mitigated if the user’s intent is known in advance or data is available to pre-train a task success predictor off-line. In practice neither of these apply for most real world applications. Here we propose an on-line learning framework whereby the dialogue policy is jointly trained alongside the reward model via active learning with a Gaussian process model. This Gaussian process operates on a continuous space dialogue representation generated in an unsupervised fashion using a recurrent neural network encoder-decoder. The experimental results demonstrate that the proposed framework is able to significantly reduce data annotation costs and mitigate noisy user feedback in dialogue policy learning.
Tasks	Active Learning, Spoken Dialogue Systems
Published	2016-05-24
URL	http://arxiv.org/abs/1605.07669v2
PDF	http://arxiv.org/pdf/1605.07669v2.pdf
PWC	https://paperswithcode.com/paper/on-line-active-reward-learning-for-policy
Repo
Framework

Egocentric Meets Top-view


Title	Egocentric Meets Top-view
Authors	Shervin Ardeshir, Ali Borji
Abstract	Thanks to the availability and increasing popularity of Egocentric cameras such as GoPro cameras, glasses, and etc. we have been provided with a plethora of videos captured from the first person perspective. Surveillance cameras and Unmanned Aerial Vehicles(also known as drones) also offer tremendous amount of videos, mostly with top-down or oblique view-point. Egocentric vision and top-view surveillance videos have been studied extensively in the past in the computer vision community. However, the relationship between the two has yet to be explored thoroughly. In this effort, we attempt to explore this relationship by approaching two questions. First, having a set of egocentric videos and a top-view video, can we verify if the top-view video contains all, or some of the egocentric viewers present in the egocentric set? And second, can we identify the egocentric viewers in the content of the top-view video? In other words, can we find the cameramen in the surveillance videos? These problems can become more challenging when the videos are not time-synchronous. Thus we formalize the problem in a way which handles and also estimates the unknown relative time-delays between the egocentric videos and the top-view video. We formulate the problem as a spectral graph matching instance, and jointly seek the optimal assignments and relative time-delays of the videos. As a result, we spatiotemporally localize the egocentric observers in the top-view video. We model each view (egocentric or top) using a graph, and compute the assignment and time-delays in an iterative-alternative fashion.
Tasks	Graph Matching
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08334v2
PDF	http://arxiv.org/pdf/1608.08334v2.pdf
PWC	https://paperswithcode.com/paper/egocentric-meets-top-view
Repo
Framework

Saliency Integration: An Arbitrator Model


Title	Saliency Integration: An Arbitrator Model
Authors	Yingyue Xu, Xiaopeng Hong, Fatih Porikli, Xin Liu, Jie Chen, Guoying Zhao
Abstract	Saliency integration has attracted much attention on unifying saliency maps from multiple saliency models. Previous offline integration methods usually face two challenges: 1. if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; 2. an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model. To address these problems, in this paper, we propose an arbitrator model (AM) for saliency integration. Firstly, we incorporate the consensus of multiple saliency models and the external knowledge into a reference map to effectively rectify the misleading by candidate models. Secondly, our quest for ways of estimating the expertise of the saliency models without ground truth labels gives rise to two distinct online model-expertise estimation methods. Finally, we derive a Bayesian integration framework to reconcile the saliency models of varying expertise and the reference map. To extensively evaluate the proposed AM model, we test twenty-seven state-of-the-art saliency models, covering both traditional and deep learning ones, on various combinations over four datasets. The evaluation results show that the AM model improves the performance substantially compared to the existing state-of-the-art integration methods, regardless of the chosen candidate saliency models.
Tasks
Published	2016-08-04
URL	http://arxiv.org/abs/1608.01536v2
PDF	http://arxiv.org/pdf/1608.01536v2.pdf
PWC	https://paperswithcode.com/paper/saliency-integration-an-arbitrator-model
Repo
Framework

Log-Linear RNNs: Towards Recurrent Neural Networks with Flexible Prior Knowledge


Title	Log-Linear RNNs: Towards Recurrent Neural Networks with Flexible Prior Knowledge
Authors	Marc Dymetman, Chunyang Xiao
Abstract	We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a special case. This conceptually simple move has two main advantages. First, it allows the learner to combat training data sparsity by allowing it to model words (or more generally, output symbols) as complex combinations of attributes without requiring that each combination is directly observed in the training data (as the softmax does). Second, it permits the inclusion of flexible prior knowledge in the form of a priori specified modular features, where the neural network component learns to dynamically control the weights of a log-linear distribution exploiting these features. We conduct experiments in the domain of language modelling of French, that exploit morphological prior knowledge and show an important decrease in perplexity relative to a baseline RNN. We provide other motivating iillustrations, and finally argue that the log-linear and the neural-network components contribute complementary strengths to the LL-RNN: the LL aspect allows the model to incorporate rich prior knowledge, while the NN aspect, according to the “representation learning” paradigm, allows the model to discover novel combination of characteristics.
Tasks	Language Modelling, Representation Learning
Published	2016-07-08
URL	http://arxiv.org/abs/1607.02467v2
PDF	http://arxiv.org/pdf/1607.02467v2.pdf
PWC	https://paperswithcode.com/paper/log-linear-rnns-towards-recurrent-neural
Repo
Framework

Enabling Dark Energy Science with Deep Generative Models of Galaxy Images


Title	Enabling Dark Energy Science with Deep Generative Models of Galaxy Images
Authors	Siamak Ravanbakhsh, Francois Lanusse, Rachel Mandelbaum, Jeff Schneider, Barnabas Poczos
Abstract	Understanding the nature of dark energy, the mysterious force driving the accelerated expansion of the Universe, is a major challenge of modern cosmology. The next generation of cosmological surveys, specifically designed to address this issue, rely on accurate measurements of the apparent shapes of distant galaxies. However, shape measurement methods suffer from various unavoidable biases and therefore will rely on a precise calibration to meet the accuracy requirements of the science analysis. This calibration process remains an open challenge as it requires large sets of high quality galaxy images. To this end, we study the application of deep conditional generative models in generating realistic galaxy images. In particular we consider variations on conditional variational autoencoder and introduce a new adversarial objective for training of conditional generative networks. Our results suggest a reliable alternative to the acquisition of expensive high quality observations for generating the calibration data needed by the next generation of cosmological surveys.
Tasks	Calibration
Published	2016-09-19
URL	http://arxiv.org/abs/1609.05796v2
PDF	http://arxiv.org/pdf/1609.05796v2.pdf
PWC	https://paperswithcode.com/paper/enabling-dark-energy-science-with-deep
Repo
Framework

Fair prediction with disparate impact: A study of bias in recidivism prediction instruments


Title	Fair prediction with disparate impact: A study of bias in recidivism prediction instruments
Authors	Alexandra Chouldechova
Abstract	Recidivism prediction instruments provide decision makers with an assessment of the likelihood that a criminal defendant will reoffend at a future point in time. While such instruments are gaining increasing popularity across the country, their use is attracting tremendous controversy. Much of the controversy concerns potential discriminatory bias in the risk assessments that are produced. This paper discusses a fairness criterion originating in the field of educational and psychological testing that has recently been applied to assess the fairness of recidivism prediction instruments. We demonstrate how adherence to the criterion may lead to considerable disparate impact when recidivism prevalence differs across groups.
Tasks
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07524v1
PDF	http://arxiv.org/pdf/1610.07524v1.pdf
PWC	https://paperswithcode.com/paper/fair-prediction-with-disparate-impact-a-study
Repo
Framework

UBL: an R package for Utility-based Learning


Title	UBL: an R package for Utility-based Learning
Authors	Paula Branco, Rita P. Ribeiro, Luis Torgo
Abstract	This document describes the R package UBL that allows the use of several methods for handling utility-based learning problems. Classification and regression problems that assume non-uniform costs and/or benefits pose serious challenges to predictive analytic tasks. In the context of meteorology, finance, medicine, ecology, among many other, specific domain information concerning the preference bias of the users must be taken into account to enhance the models predictive performance. To deal with this problem, a large number of techniques was proposed by the research community for both classification and regression tasks. The main goal of UBL package is to facilitate the utility-based predictive analytic task by providing a set of methods to deal with this type of problems in the R environment. It is a versatile tool that provides mechanisms to handle both regression and classification (binary and multiclass) tasks. Moreover, UBL package allows the user to specify his domain preferences, but it also provides some automatic methods that try to infer those preference bias from the domain, considering some common known settings.
Tasks
Published	2016-04-27
URL	http://arxiv.org/abs/1604.08079v2
PDF	http://arxiv.org/pdf/1604.08079v2.pdf
PWC	https://paperswithcode.com/paper/ubl-an-r-package-for-utility-based-learning
Repo
Framework