May 5, 2019

3315 words 16 mins read

Paper Group ANR 451

Classification of Alzheimer’s Disease using fMRI Data and Deep Learning Convolutional Neural Networks. Modeling and Inferring Human Intents and Latent Functional Objects for Trajectory Prediction. Towards Bayesian Deep Learning: A Framework and Some Existing Methods. Video Analysis of “YouTube Funnies” to Aid the Study of Human Gait and Falls - Pre …

Classification of Alzheimer’s Disease using fMRI Data and Deep Learning Convolutional Neural Networks


Title	Classification of Alzheimer’s Disease using fMRI Data and Deep Learning Convolutional Neural Networks
Authors	Saman Sarraf, Ghassem Tofighi
Abstract	Over the past decade, machine learning techniques especially predictive modeling and pattern recognition in biomedical sciences from drug delivery system to medical imaging has become one of the important methods which are assisting researchers to have deeper understanding of entire issue and to solve complex medical problems. Deep learning is power learning machine learning algorithm in classification while extracting high-level features. In this paper, we used convolutional neural network to classify Alzheimer’s brain from normal healthy brain. The importance of classifying this kind of medical data is to potentially develop a predict model or system in order to recognize the type disease from normal subjects or to estimate the stage of the disease. Classification of clinical data such as Alzheimer’s disease has been always challenging and most problematic part has been always selecting the most discriminative features. Using Convolutional Neural Network (CNN) and the famous architecture LeNet-5, we successfully classified functional MRI data of Alzheimer’s subjects from normal controls where the accuracy of test data on trained data reached 96.85%. This experiment suggests us the shift and scale invariant features extracted by CNN followed by deep learning classification is most powerful method to distinguish clinical data from healthy data in fMRI. This approach also enables us to expand our methodology to predict more complicated systems.
Tasks
Published	2016-03-29
URL	http://arxiv.org/abs/1603.08631v1
PDF	http://arxiv.org/pdf/1603.08631v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-alzheimers-disease-using
Repo
Framework

Modeling and Inferring Human Intents and Latent Functional Objects for Trajectory Prediction


Title	Modeling and Inferring Human Intents and Latent Functional Objects for Trajectory Prediction
Authors	Dan Xie, Tianmin Shu, Sinisa Todorovic, Song-Chun Zhu
Abstract	This paper is about detecting functional objects and inferring human intentions in surveillance videos of public spaces. People in the videos are expected to intentionally take shortest paths toward functional objects subject to obstacles, where people can satisfy certain needs (e.g., a vending machine can quench thirst), by following one of three possible intent behaviors: reach a single functional object and stop, or sequentially visit several functional objects, or initially start moving toward one goal but then change the intent to move toward another. Since detecting functional objects in low-resolution surveillance videos is typically unreliable, we call them “dark matter” characterized by the functionality to attract people. We formulate the Agent-based Lagrangian Mechanics wherein human trajectories are probabilistically modeled as motions of agents in many layers of “dark-energy” fields, where each agent can select a particular force field to affect its motions, and thus define the minimum-energy Dijkstra path toward the corresponding source “dark matter”. For evaluation, we compiled and annotated a new dataset. The results demonstrate our effectiveness in predicting human intent behaviors and trajectories, and localizing functional objects, as well as discovering distinct functional classes of objects by clustering human motion behavior in the vicinity of functional objects.
Tasks	Trajectory Prediction
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07827v1
PDF	http://arxiv.org/pdf/1606.07827v1.pdf
PWC	https://paperswithcode.com/paper/modeling-and-inferring-human-intents-and
Repo
Framework

Towards Bayesian Deep Learning: A Framework and Some Existing Methods


Title	Towards Bayesian Deep Learning: A Framework and Some Existing Methods
Authors	Hao Wang, Dit-Yan Yeung
Abstract	While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, the subsequent tasks that involve inference, reasoning and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. To achieve integrated intelligence that involves both perception and inference, it is naturally desirable to tightly integrate deep learning and Bayesian models within a principled probabilistic framework, which we call Bayesian deep learning. In this unified framework, the perception of text or images using deep learning can boost the performance of higher-level inference and in return, the feedback from the inference process is able to enhance the perception of text or images. This paper proposes a general framework for Bayesian deep learning and reviews its recent applications on recommender systems, topic models, and control. In this paper, we also discuss the relationship and differences between Bayesian deep learning and other related topics like Bayesian treatment of neural networks.
Tasks	Object Recognition, Recommendation Systems, Topic Models
Published	2016-08-24
URL	http://arxiv.org/abs/1608.06884v2
PDF	http://arxiv.org/pdf/1608.06884v2.pdf
PWC	https://paperswithcode.com/paper/towards-bayesian-deep-learning-a-framework
Repo
Framework

Video Analysis of “YouTube Funnies” to Aid the Study of Human Gait and Falls - Preliminary Results and Proof of Concept


Title	Video Analysis of “YouTube Funnies” to Aid the Study of Human Gait and Falls - Preliminary Results and Proof of Concept
Authors	Babak Taati, Pranay Lohia, Avril Mansfield, Ahmed Ashraf
Abstract	Because falls are funny, YouTube and other video sharing sites contain a large repository of real-life falls. We propose extracting gait and balance information from these videos to help us better understand some of the factors that contribute to falls. Proof-of-concept is explored in a single video containing multiple (n=14) falls/non-falls in the presence of an unexpected obstacle. The analysis explores: computing spatiotemporal parameters of gait in a video captured from an arbitrary viewpoint; the relationship between parameters of gait from the last few steps before the obstacle and falling vs. not falling; and the predictive capacity of a multivariate model in predicting a fall in the presence of an unexpected obstacle. Homography transformations correct the perspective projection distortion and allow for the consistent tracking of gait parameters as an individual walks in an arbitrary direction in the scene. A synthetic top view allows for computing the average stride length and a synthetic side view allows for measuring up and down motions of the head. In leave-one-out cross-validation, we were able to correctly predict whether a person would fall or not in 11 out of the 14 cases (78.6%), just by looking at the average stride length and the range of vertical head motion during the 1-4 most recent steps prior to reaching the obstacle.
Tasks
Published	2016-10-26
URL	http://arxiv.org/abs/1610.08400v1
PDF	http://arxiv.org/pdf/1610.08400v1.pdf
PWC	https://paperswithcode.com/paper/video-analysis-of-youtube-funnies-to-aid-the
Repo
Framework

Comprehensive Evaluation of OpenCL-based Convolutional Neural Network Accelerators in Xilinx and Altera FPGAs


Title	Comprehensive Evaluation of OpenCL-based Convolutional Neural Network Accelerators in Xilinx and Altera FPGAs
Authors	R. Tapiador, A. Rios-Navarro, A. Linares-Barranco, Minkyu Kim, Deepak Kadetotad, Jae-sun Seo
Abstract	Deep learning has significantly advanced the state of the art in artificial intelligence, gaining wide popularity from both industry and academia. Special interest is around Convolutional Neural Networks (CNN), which take inspiration from the hierarchical structure of the visual cortex, to form deep layers of convolutional operations, along with fully connected classifiers. Hardware implementations of these deep CNN architectures are challenged with memory bottlenecks that require many convolution and fully-connected layers demanding large amount of communication for parallel computation. Multi-core CPU based solutions have demonstrated their inadequacy for this problem due to the memory wall and low parallelism. Many-core GPU architectures show superior performance but they consume high power and also have memory constraints due to inconsistencies between cache and main memory. FPGA design solutions are also actively being explored, which allow implementing the memory hierarchy using embedded BlockRAM. This boosts the parallel use of shared memory elements between multiple processing units, avoiding data replicability and inconsistencies. This makes FPGAs potentially powerful solutions for real-time classification of CNNs. Both Altera and Xilinx have adopted OpenCL co-design framework from GPU for FPGA designs as a pseudo-automatic development solution. In this paper, a comprehensive evaluation and comparison of Altera and Xilinx OpenCL frameworks for a 5-layer deep CNN is presented. Hardware resources, temporal performance and the OpenCL architecture for CNNs are discussed. Xilinx demonstrates faster synthesis, better FPGA resource utilization and more compact boards. Altera provides multi-platforms tools, mature design community and better execution times.
Tasks
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09296v1
PDF	http://arxiv.org/pdf/1609.09296v1.pdf
PWC	https://paperswithcode.com/paper/comprehensive-evaluation-of-opencl-based
Repo
Framework

Analyzing features learned for Offline Signature Verification using Deep CNNs


Title	Analyzing features learned for Offline Signature Verification using Deep CNNs
Authors	Luiz G. Hafemann, Robert Sabourin, Luiz S. Oliveira
Abstract	Research on Offline Handwritten Signature Verification explored a large variety of handcrafted feature extractors, ranging from graphology, texture descriptors to interest points. In spite of advancements in the last decades, performance of such systems is still far from optimal when we test the systems against skilled forgeries - signature forgeries that target a particular individual. In previous research, we proposed a formulation of the problem to learn features from data (signature images) in a Writer-Independent format, using Deep Convolutional Neural Networks (CNNs), seeking to improve performance on the task. In this research, we push further the performance of such method, exploring a range of architectures, and obtaining a large improvement in state-of-the-art performance on the GPDS dataset, the largest publicly available dataset on the task. In the GPDS-160 dataset, we obtained an Equal Error Rate of 2.74%, compared to 6.97% in the best result published in literature (that used a combination of multiple classifiers). We also present a visual analysis of the feature space learned by the model, and an analysis of the errors made by the classifier. Our analysis shows that the model is very effective in separating signatures that have a different global appearance, while being particularly vulnerable to forgeries that very closely resemble genuine signatures, even if their line quality is bad, which is the case of slowly-traced forgeries.
Tasks
Published	2016-07-15
URL	http://arxiv.org/abs/1607.04573v2
PDF	http://arxiv.org/pdf/1607.04573v2.pdf
PWC	https://paperswithcode.com/paper/analyzing-features-learned-for-offline
Repo
Framework

One Class Splitting Criteria for Random Forests


Title	One Class Splitting Criteria for Random Forests
Authors	Nicolas Goix, Nicolas Drougard, Romain Brault, Maël Chiapino
Abstract	Random Forests (RFs) are strong machine learning tools for classification and regression. However, they remain supervised algorithms, and no extension of RFs to the one-class setting has been proposed, except for techniques based on second-class sampling. This work fills this gap by proposing a natural methodology to extend standard splitting criteria to the one-class setting, structurally generalizing RFs to one-class classification. An extensive benchmark of seven state-of-the-art anomaly detection algorithms is also presented. This empirically demonstrates the relevance of our approach.
Tasks	Anomaly Detection
Published	2016-11-07
URL	http://arxiv.org/abs/1611.01971v3
PDF	http://arxiv.org/pdf/1611.01971v3.pdf
PWC	https://paperswithcode.com/paper/one-class-splitting-criteria-for-random
Repo
Framework

Hardness of the Pricing Problem for Chains in Barter Exchanges


Title	Hardness of the Pricing Problem for Chains in Barter Exchanges
Authors	Benjamin Plaut, John P. Dickerson, Tuomas Sandholm
Abstract	Kidney exchange is a barter market where patients trade willing but medically incompatible donors. These trades occur via cycles, where each patient-donor pair both gives and receives a kidney, and via chains, which begin with an altruistic donor who does not require a kidney in return. For logistical reasons, the maximum length of a cycle is typically limited to a small constant, while chains can be much longer. Given a compatibility graph of patient-donor pairs, altruists, and feasible potential transplants between them, finding even a maximum-cardinality set of vertex-disjoint cycles and chains is NP-hard. There has been much work on developing provably optimal solvers that are efficient in practice. One of the leading techniques has been branch and price, where column generation is used to incrementally bring cycles and chains into the optimization model on an as-needed basis. In particular, only positive-price columns need to be brought into the model. We prove that finding a positive-price chain is NP-complete. This shows incorrectness of two leading branch-and-price solvers that suggested polynomial-time chain pricing algorithms.
Tasks
Published	2016-06-01
URL	http://arxiv.org/abs/1606.00117v1
PDF	http://arxiv.org/pdf/1606.00117v1.pdf
PWC	https://paperswithcode.com/paper/hardness-of-the-pricing-problem-for-chains-in
Repo
Framework

Epistemic Protocols for Distributed Gossiping


Title	Epistemic Protocols for Distributed Gossiping
Authors	Krzysztof R. Apt, Davide Grossi, Wiebe van der Hoek
Abstract	Gossip protocols aim at arriving, by means of point-to-point or group communications, at a situation in which all the agents know each other’s secrets. We consider distributed gossip protocols which are expressed by means of epistemic logic. We provide an operational semantics of such protocols and set up an appropriate framework to argue about their correctness. Then we analyze specific protocols for complete graphs and for directed rings.
Tasks
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07516v1
PDF	http://arxiv.org/pdf/1606.07516v1.pdf
PWC	https://paperswithcode.com/paper/epistemic-protocols-for-distributed-gossiping
Repo
Framework

Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video


Title	Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video
Authors	Zhiwu Huang, Ruiping Wang, Shiguang Shan, Luc Van Gool, Xilin Chen
Abstract	Riemannian manifolds have been widely employed for video representations in visual classification tasks including video-based face recognition. The success mainly derives from learning a discriminant Riemannian metric which encodes the non-linear geometry of the underlying Riemannian manifolds. In this paper, we propose a novel metric learning framework to learn a distance metric across a Euclidean space and a Riemannian manifold to fuse the average appearance and pattern variation of faces within one video. The proposed metric learning framework can handle three typical tasks of video-based face recognition: Video-to-Still, Still-to-Video and Video-to-Video settings. To accomplish this new framework, by exploiting typical Riemannian geometries for kernel embedding, we map the source Euclidean space and Riemannian manifold into a common Euclidean subspace, each through a corresponding high-dimensional Reproducing Kernel Hilbert Space (RKHS). With this mapping, the problem of learning a cross-view metric between the two source heterogeneous spaces can be expressed as learning a single-view Euclidean distance metric in the target common Euclidean space. By learning information on heterogeneous data with the shared label, the discriminant metric in the common space improves face recognition from videos. Extensive experiments on four challenging video face databases demonstrate that the proposed framework has a clear advantage over the state-of-the-art methods in the three classical video-based face recognition tasks.
Tasks	Face Recognition, Metric Learning
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04200v2
PDF	http://arxiv.org/pdf/1608.04200v2.pdf
PWC	https://paperswithcode.com/paper/cross-euclidean-to-riemannian-metric-learning
Repo
Framework

CompAdaGrad: A Compressed, Complementary, Computationally-Efficient Adaptive Gradient Method


Title	CompAdaGrad: A Compressed, Complementary, Computationally-Efficient Adaptive Gradient Method
Authors	Nishant A. Mehta, Alistair Rendell, Anish Varghese, Christfried Webers
Abstract	The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. The method’s full-matrix incarnation offers much better theoretical guarantees and potentially better empirical performance than its diagonal version; however, this version is computationally prohibitive and so the simpler diagonal version often is used in practice. We introduce a new method, CompAdaGrad, that navigates the space between these two schemes and show that this method can yield results much better than diagonal AdaGrad while avoiding the (effectively intractable) $O(n^3)$ computational complexity of full-matrix AdaGrad for dimension $n$. CompAdaGrad essentially performs full-matrix regularization in a low-dimensional subspace while performing diagonal regularization in the complementary subspace. We derive CompAdaGrad’s updates for composite mirror descent in case of the squared $\ell_2$ norm and the $\ell_1$ norm, demonstrate that its complexity per iteration is linear in the dimension, and establish guarantees for the method independent of the choice of composite regularizer. Finally, we show preliminary results on several datasets.
Tasks
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03319v2
PDF	http://arxiv.org/pdf/1609.03319v2.pdf
PWC	https://paperswithcode.com/paper/compadagrad-a-compressed-complementary
Repo
Framework

An Efficient Method for Robust Projection Matrix Design


Title	An Efficient Method for Robust Projection Matrix Design
Authors	Tao Hong, Zhihui Zhu
Abstract	Our objective is to efficiently design a robust projection matrix $\Phi$ for the Compressive Sensing (CS) systems when applied to the signals that are not exactly sparse. The optimal projection matrix is obtained by mainly minimizing the average coherence of the equivalent dictionary. In order to drop the requirement of the sparse representation error (SRE) for a set of training data as in [15] [16], we introduce a novel penalty function independent of a particular SRE matrix. Without requiring of training data, we can efficiently design the robust projection matrix and apply it for most of CS systems, like a CS system for image processing with a conventional wavelet dictionary in which the SRE matrix is generally not available. Simulation results demonstrate the efficiency and effectiveness of the proposed approach compared with the state-of-the-art methods. In addition, we experimentally demonstrate with natural images that under similar compression rate, a CS system with a learned dictionary in high dimensions outperforms the one in low dimensions in terms of reconstruction accuracy. This together with the fact that our proposed method can efficiently work in high dimension suggests that a CS system can be potentially implemented beyond the small patches in sparsity-based image processing.
Tasks	Compressive Sensing
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08281v3
PDF	http://arxiv.org/pdf/1609.08281v3.pdf
PWC	https://paperswithcode.com/paper/an-efficient-method-for-robust-projection
Repo
Framework

Sentiment Analysis of Review Datasets Using Naive Bayes and K-NN Classifier


Title	Sentiment Analysis of Review Datasets Using Naive Bayes and K-NN Classifier
Authors	Lopamudra Dey, Sanjay Chakraborty, Anuraag Biswas, Beepa Bose, Sweta Tiwari
Abstract	The advent of Web 2.0 has led to an increase in the amount of sentimental content available in the Web. Such content is often found in social media web sites in the form of movie or product reviews, user comments, testimonials, messages in discussion forums etc. Timely discovery of the sentimental or opinionated web content has a number of advantages, the most important of all being monetization. Understanding of the sentiments of human masses towards different entities and products enables better services for contextual advertisements, recommendation systems and analysis of market trends. The focus of our project is sentiment focussed web crawling framework to facilitate the quick discovery of sentimental contents of movie reviews and hotel reviews and analysis of the same. We use statistical methods to capture elements of subjective style and the sentence polarity. The paper elaborately discusses two supervised machine learning algorithms: K-Nearest Neighbour(K-NN) and Naive Bayes and compares their overall accuracy, precisions as well as recall values. It was seen that in case of movie reviews Naive Bayes gave far better results than K-NN but for hotel reviews these algorithms gave lesser, almost same accuracies.
Tasks	Recommendation Systems, Sentiment Analysis
Published	2016-10-31
URL	http://arxiv.org/abs/1610.09982v1
PDF	http://arxiv.org/pdf/1610.09982v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-of-review-datasets-using
Repo
Framework

An Information Criterion for Inferring Coupling in Distributed Dynamical Systems


Title	An Information Criterion for Inferring Coupling in Distributed Dynamical Systems
Authors	Oliver M. Cliff, Mikhail Prokopenko, Robert Fitch
Abstract	The behaviour of many real-world phenomena can be modelled by nonlinear dynamical systems whereby a latent system state is observed through a filter. We are interested in interacting subsystems of this form, which we model by a set of coupled maps as a synchronous update graph dynamical systems. Specifically, we study the structure learning problem for spatially distributed dynamical systems coupled via a directed acyclic graph. Unlike established structure learning procedures that find locally maximum posterior probabilities of a network structure containing latent variables, our work exploits the properties of dynamical systems to compute globally optimal approximations of these distributions. We arrive at this result by the use of time delay embedding theorems. Taking an information-theoretic perspective, we show that the log-likelihood has an intuitive interpretation in terms of information transfer.
Tasks
Published	2016-05-23
URL	http://arxiv.org/abs/1605.06931v3
PDF	http://arxiv.org/pdf/1605.06931v3.pdf
PWC	https://paperswithcode.com/paper/an-information-criterion-for-inferring
Repo
Framework

Neural Machine Translation with Recurrent Attention Modeling


Title	Neural Machine Translation with Recurrent Attention Modeling
Authors	Zichao Yang, Zhiting Hu, Yuntian Deng, Chris Dyer, Alex Smola
Abstract	Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the future. We improve upon the attention model of Bahdanau et al. (2014) by explicitly modeling the relationship between previous and subsequent attention levels for each word using one recurrent network per input word. This architecture easily captures informative features, such as fertility and regularities in relative distortion. In experiments, we show our parameterization of attention improves translation quality.
Tasks	Machine Translation
Published	2016-07-18
URL	http://arxiv.org/abs/1607.05108v1
PDF	http://arxiv.org/pdf/1607.05108v1.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-with-recurrent
Repo
Framework