May 6, 2019

3294 words 16 mins read

Paper Group ANR 292

Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes. Relativistic Monte Carlo. A multiple instance learning approach for sequence data with across bag dependencies. Learning to Search on Manifolds for 3D Pose Estimation of Articulated Objects. Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of D …

Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes


Title	Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes
Authors	Corinne L. Jones, Sham M. Kakade, Lucas W. Thornblade, David R. Flum, Abraham D. Flaxman
Abstract	We propose using canonical correlation analysis (CCA) to generate features from sequences of medical billing codes. Applying this novel use of CCA to a database of medical billing codes for patients with diverticulitis, we first demonstrate that the CCA embeddings capture meaningful relationships among the codes. We then generate features from these embeddings and establish their usefulness in predicting future elective surgery for diverticulitis, an important marker in efforts for reducing costs in healthcare.
Tasks
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00516v2
PDF	http://arxiv.org/pdf/1612.00516v2.pdf
PWC	https://paperswithcode.com/paper/canonical-correlation-analysis-for-analyzing
Repo
Framework

Relativistic Monte Carlo


Title	Relativistic Monte Carlo
Authors	Xiaoyu Lu, Valerio Perrone, Leonard Hasenclever, Yee Whye Teh, Sebastian J. Vollmer
Abstract	Hamiltonian Monte Carlo (HMC) is a popular Markov chain Monte Carlo (MCMC) algorithm that generates proposals for a Metropolis-Hastings algorithm by simulating the dynamics of a Hamiltonian system. However, HMC is sensitive to large time discretizations and performs poorly if there is a mismatch between the spatial geometry of the target distribution and the scales of the momentum distribution. In particular the mass matrix of HMC is hard to tune well. In order to alleviate these problems we propose relativistic Hamiltonian Monte Carlo, a version of HMC based on relativistic dynamics that introduce a maximum velocity on particles. We also derive stochastic gradient versions of the algorithm and show that the resulting algorithms bear interesting relationships to gradient clipping, RMSprop, Adagrad and Adam, popular optimisation methods in deep learning. Based on this, we develop relativistic stochastic gradient descent by taking the zero-temperature limit of relativistic stochastic gradient Hamiltonian Monte Carlo. In experiments we show that the relativistic algorithms perform better than classical Newtonian variants and Adam.
Tasks
Published	2016-09-14
URL	http://arxiv.org/abs/1609.04388v1
PDF	http://arxiv.org/pdf/1609.04388v1.pdf
PWC	https://paperswithcode.com/paper/relativistic-monte-carlo
Repo
Framework

A multiple instance learning approach for sequence data with across bag dependencies


Title	A multiple instance learning approach for sequence data with across bag dependencies
Authors	Manel Zoghlami, Sabeur Aridhi, Haitham Sghaier, Mondher Maddouri, Engelbert Mephu Nguifo
Abstract	In Multiple Instance Learning (MIL) problem for sequence data, the learning data consist of a set of bags where each bag contains a set of instances/sequences. In many real world applications such as bioinformatics, web mining, and text mining, comparing a random couple of sequences makes no sense. In fact, each instance of each bag may have structural and/or temporal relation with other instances in other bags. Thus, the classification task should take into account the relation between semantically related instances across bags. In this paper, we present two novel MIL approaches for sequence data classification: (1) ABClass and (2) ABSim. In ABClass, each sequence is represented by one vector of attributes. For each sequence of the unknown bag, a discriminative classifier is applied in order to compute a partial classification result. Then, an aggregation method is applied to these partial results in order to generate the final result. In ABSim, we use a similarity measure between each sequence of the unknown bag and the corresponding sequences in the learning bags. An unknown bag is labeled with the bag that presents more similar sequences. We applied both approaches to the problem of bacterial Ionizing Radiation Resistance (IRR) prediction. We evaluated and discussed the proposed approaches on well known Ionizing Radiation Resistance Bacteria (IRRB) and Ionizing Radiation Sensitive Bacteria (IRSB) represented by primary structure of basal DNA repair proteins. The experimental results show that both ABClass and ABSim approaches are efficient.
Tasks	Multiple Instance Learning
Published	2016-01-30
URL	http://arxiv.org/abs/1602.00163v1
PDF	http://arxiv.org/pdf/1602.00163v1.pdf
PWC	https://paperswithcode.com/paper/a-multiple-instance-learning-approach-for
Repo
Framework

Learning to Search on Manifolds for 3D Pose Estimation of Articulated Objects


Title	Learning to Search on Manifolds for 3D Pose Estimation of Articulated Objects
Authors	Yu Zhang, Chi Xu, Li Cheng
Abstract	This paper focuses on the challenging problem of 3D pose estimation of a diverse spectrum of articulated objects from single depth images. A novel structured prediction approach is considered, where 3D poses are represented as skeletal models that naturally operate on manifolds. Given an input depth image, the problem of predicting the most proper articulation of underlying skeletal model is thus formulated as sequentially searching for the optimal skeletal configuration. This is subsequently addressed by convolutional neural nets trained end-to-end to render sequential prediction of the joint locations as regressing a set of tangent vectors of the underlying manifolds. Our approach is examined on various articulated objects including human hand, mouse, and fish benchmark datasets. Empirically it is shown to deliver highly competitive performance with respect to the state-of-the-arts, while operating in real-time (over 30 FPS).
Tasks	3D Pose Estimation, Pose Estimation, Structured Prediction
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00596v1
PDF	http://arxiv.org/pdf/1612.00596v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-search-on-manifolds-for-3d-pose
Repo
Framework

Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks


Title	Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks
Authors	Arash Ardakani, Carlo Condo, Warren J. Gross
Abstract	Recently deep neural networks have received considerable attention due to their ability to extract and represent high-level abstractions in data sets. Deep neural networks such as fully-connected and convolutional neural networks have shown excellent performance on a wide range of recognition and classification tasks. However, their hardware implementations currently suffer from large silicon area and high power consumption due to the their high degree of complexity. The power/energy consumption of neural networks is dominated by memory accesses, the majority of which occur in fully-connected networks. In fact, they contain most of the deep neural network parameters. In this paper, we propose sparsely-connected networks, by showing that the number of connections in fully-connected networks can be reduced by up to 90% while improving the accuracy performance on three popular datasets (MNIST, CIFAR10 and SVHN). We then propose an efficient hardware architecture based on linear-feedback shift registers to reduce the memory requirements of the proposed sparsely-connected networks. The proposed architecture can save up to 90% of memory compared to the conventional implementations of fully-connected neural networks. Moreover, implementation results show up to 84% reduction in the energy consumption of a single neuron of the proposed sparsely-connected networks compared to a single neuron of fully-connected neural networks.
Tasks
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01427v3
PDF	http://arxiv.org/pdf/1611.01427v3.pdf
PWC	https://paperswithcode.com/paper/sparsely-connected-neural-networks-towards
Repo
Framework

A Searchlight Factor Model Approach for Locating Shared Information in Multi-Subject fMRI Analysis


Title	A Searchlight Factor Model Approach for Locating Shared Information in Multi-Subject fMRI Analysis
Authors	Hejia Zhang, Po-Hsuan Chen, Janice Chen, Xia Zhu, Javier S. Turek, Theodore L. Willke, Uri Hasson, Peter J. Ramadge
Abstract	There is a growing interest in joint multi-subject fMRI analysis. The challenge of such analysis comes from inherent anatomical and functional variability across subjects. One approach to resolving this is a shared response factor model. This assumes a shared and time synchronized stimulus across subjects. Such a model can often identify shared information, but it may not be able to pinpoint with high resolution the spatial location of this information. In this work, we examine a searchlight based shared response model to identify shared information in small contiguous regions (searchlights) across the whole brain. Validation using classification tasks demonstrates that we can pinpoint informative local regions.
Tasks
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09432v1
PDF	http://arxiv.org/pdf/1609.09432v1.pdf
PWC	https://paperswithcode.com/paper/a-searchlight-factor-model-approach-for
Repo
Framework

The Bayesian SLOPE


Title	The Bayesian SLOPE
Authors	Amir Sepehri
Abstract	The SLOPE estimates regression coefficients by minimizing a regularized residual sum of squares using a sorted-$\ell_1$-norm penalty. The SLOPE combines testing and estimation in regression problems. It exhibits suitable variable selection and prediction properties, as well as minimax optimality. This paper introduces the Bayesian SLOPE procedure for linear regression. The classical SLOPE estimate is the posterior mode in the normal regression problem with an appropriate prior on the coefficients. The Bayesian SLOPE considers the full Bayesian model and has the advantage of offering credible sets and standard error estimates for the parameters. Moreover, the hierarchical Bayesian framework allows for full Bayesian and empirical Bayes treatment of the penalty coefficients; whereas it is not clear how to choose these coefficients when using the SLOPE on a general design matrix. A direct characterization of the posterior is provided which suggests a Gibbs sampler that does not involve latent variables. An efficient hybrid Gibbs sampler for the Bayesian SLOPE is introduced. Point estimation using the posterior mean is highlighted, which automatically facilitates the Bayesian prediction of future observations. These are demonstrated on real and synthetic data.
Tasks
Published	2016-08-31
URL	http://arxiv.org/abs/1608.08968v2
PDF	http://arxiv.org/pdf/1608.08968v2.pdf
PWC	https://paperswithcode.com/paper/the-bayesian-slope
Repo
Framework


Title	Learning Aligned Cross-Modal Representations from Weakly Aligned Data
Authors	Lluis Castrejon, Yusuf Aytar, Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
Abstract	People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize cross-modal scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for cross-modal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic of the modality. Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval. Moreover, our visualizations suggest that units emerge in the shared representation that tend to activate on consistent concepts independently of the modality.
Tasks
Published	2016-07-25
URL	http://arxiv.org/abs/1607.07295v1
PDF	http://arxiv.org/pdf/1607.07295v1.pdf
PWC	https://paperswithcode.com/paper/learning-aligned-cross-modal-representations
Repo
Framework

Fast and Accurate Performance Analysis of LTE Radio Access Networks


Title	Fast and Accurate Performance Analysis of LTE Radio Access Networks
Authors	Anand Padmanabha Iyer, Ion Stoica, Mosharaf Chowdhury, Li Erran Li
Abstract	An increasing amount of analytics is performed on data that is procured in a real-time fashion to make real-time decisions. Such tasks include simple reporting on streams to sophisticated model building. However, the practicality of such analyses are impeded in several domains because they are faced with a fundamental trade-off between data collection latency and analysis accuracy. In this paper, we study this trade-off in the context of a specific domain, Cellular Radio Access Networks (RAN). Our choice of this domain is influenced by its commonalities with several other domains that produce real-time data, our access to a large live dataset, and their real-time nature and dimensionality which makes it a natural fit for a popular analysis technique, machine learning (ML). We find that the latency accuracy trade-off can be resolved using two broad, general techniques: intelligent data grouping and task formulations that leverage domain characteristics. Based on this, we present CellScope, a system that addresses this challenge by applying a domain specific formulation and application of Multi-task Learning (MTL) to RAN performance analysis. It achieves this goal using three techniques: feature engineering to transform raw data into effective features, a PCA inspired similarity metric to group data from geographically nearby base stations sharing performance commonalities, and a hybrid online-offline model for efficient model updates. Our evaluation of CellScope shows that its accuracy improvements over direct application of ML range from 2.5x to 4.4x while reducing the model update overhead by up to 4.8x. We have also used CellScope to analyze a live LTE consisting of over 2 million subscribers for a period of over 10 months, where it uncovered several problems and insights, some of them previously unknown.
Tasks	Feature Engineering, Multi-Task Learning
Published	2016-05-16
URL	http://arxiv.org/abs/1605.04652v2
PDF	http://arxiv.org/pdf/1605.04652v2.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-performance-analysis-of-lte
Repo
Framework

Face Attribute Prediction Using Off-the-Shelf CNN Features


Title	Face Attribute Prediction Using Off-the-Shelf CNN Features
Authors	Yang Zhong, Josephine Sullivan, Haibo Li
Abstract	Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks — face localization, facial descriptor construction, and attribute classification — in a pipeline. As a typical classification problem, face attribute prediction has been addressed using deep learning. Current state-of-the-art performance was achieved by using two cascaded Convolutional Neural Networks (CNNs), which were specifically trained to learn face localization and attribute description. In this paper, we experiment with an alternative way of employing the power of deep representations from CNNs. Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors. Recognizing that the describable face attributes are diverse, our face descriptors are constructed from different levels of the CNNs for different attributes to best facilitate face attribute prediction. Experiments on two large datasets, LFWA and CelebA, show that our approach is entirely comparable to the state-of-the-art. Our findings not only demonstrate an efficient face attribute prediction approach, but also raise an important question: how to leverage the power of off-the-shelf CNN representations for novel tasks.
Tasks	Face Recognition
Published	2016-02-12
URL	http://arxiv.org/abs/1602.03935v2
PDF	http://arxiv.org/pdf/1602.03935v2.pdf
PWC	https://paperswithcode.com/paper/face-attribute-prediction-using-off-the-shelf
Repo
Framework

Speaker Recognition for Children’s Speech


Title	Speaker Recognition for Children’s Speech
Authors	Saeid Safavi, Maryam Najafian, Abualsoud Hanani, Martin J Russell, Peter Jancovic, Michael J Carey
Abstract	This paper presents results on Speaker Recognition (SR) for children’s speech, using the OGI Kids corpus and GMM-UBM and GMM-SVM SR systems. Regions of the spectrum containing important speaker information for children are identified by conducting SR experiments over 21 frequency bands. As for adults, the spectrum can be split into four regions, with the first (containing primary vocal tract resonance information) and third (corresponding to high frequency speech sounds) being most useful for SR. However, the frequencies at which these regions occur are from 11% to 38% higher for children. It is also noted that subband SR rates are lower for younger children. Finally results are presented of SR experiments to identify a child in a class (30 children, similar age) and school (288 children, varying ages). Class performance depends on age, with accuracy varying from 90% for young children to 99% for older children. The identification rate achieved for a child in a school is 81%.
Tasks	Speaker Recognition
Published	2016-09-23
URL	http://arxiv.org/abs/1609.07498v1
PDF	http://arxiv.org/pdf/1609.07498v1.pdf
PWC	https://paperswithcode.com/paper/speaker-recognition-for-childrens-speech
Repo
Framework

Safety Verification and Control for Collision Avoidance at Road Intersections


Title	Safety Verification and Control for Collision Avoidance at Road Intersections
Authors	Heejin Ahn, Domitilla Del Vecchio
Abstract	This paper presents the design of a supervisory algorithm that monitors safety at road intersections and overrides drivers with a safe input when necessary. The design of the supervisor consists of two parts: safety verification and control design. Safety verification is the problem to determine if vehicles will be able to cross the intersection without colliding with current drivers’ inputs. We translate this safety verification problem into a jobshop scheduling problem, which minimizes the maximum lateness and evaluates if the optimal cost is zero. The zero optimal cost corresponds to the case in which all vehicles can cross each conflict area without collisions. Computing the optimal cost requires solving a Mixed Integer Nonlinear Programming (MINLP) problem due to the nonlinear second-order dynamics of the vehicles. We therefore estimate this optimal cost by formulating two related Mixed Integer Linear Programming (MILP) problems that assume simpler vehicle dynamics. We prove that these two MILP problems yield lower and upper bounds of the optimal cost. We also quantify the worst case approximation errors of these MILP problems. We design the supervisor to override the vehicles with a safe control input if the MILP problem that computes the upper bound yields a positive optimal cost. We theoretically demonstrate that the supervisor keeps the intersection safe and is non-blocking. Computer simulations further validate that the algorithms can run in real time for problems of realistic size.
Tasks
Published	2016-12-08
URL	http://arxiv.org/abs/1612.02795v1
PDF	http://arxiv.org/pdf/1612.02795v1.pdf
PWC	https://paperswithcode.com/paper/safety-verification-and-control-for-collision
Repo
Framework

Articulated Hand Pose Estimation Review


Title	Articulated Hand Pose Estimation Review
Authors	Emad Barsoum
Abstract	With the increase number of companies focusing on commercializing Augmented Reality (AR), Virtual Reality (VR) and wearable devices, the need for a hand based input mechanism is becoming essential in order to make the experience natural, seamless and immersive. Hand pose estimation has progressed drastically in recent years due to the introduction of commodity depth cameras. Hand pose estimation based on vision is still a challenging problem due to its complexity from self-occlusion (between fingers), close similarity between fingers, dexterity of the hands, speed of the pose and the high dimension of the hand kinematic parameters. Articulated hand pose estimation is still an open problem and under intensive research from both academia and industry. The 2 approaches used for hand pose estimation are: discriminative and generative. Generative approach is a model based that tries to fit a hand model to the observed data. Discriminative approach is appearance based, usually implemented with machine learning (ML) and require a large amount of training data. Recent hand pose estimation uses hybrid approach by combining both discriminative and generative methods into a single hand pipeline. In this paper, we focus on reviewing recent progress of hand pose estimation from depth sensor. We will survey discriminative methods, generative methods and hybrid methods. This paper is not a comprehensive review of all hand pose estimation techniques, it is a subset of some of the recent state-of-the-art techniques.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06195v1
PDF	http://arxiv.org/pdf/1604.06195v1.pdf
PWC	https://paperswithcode.com/paper/articulated-hand-pose-estimation-review
Repo
Framework

Technical Report: Giving Hints for Logic Programming Examples without Revealing Solutions


Title	Technical Report: Giving Hints for Logic Programming Examples without Revealing Solutions
Authors	Gokhan Avci, Mustafa Mehuljic, Peter Schüller
Abstract	We introduce a framework for supporting learning to program in the paradigm of Answer Set Programming (ASP), which is a declarative logic programming formalism. Based on the idea of teaching by asking the student to complete small example ASP programs, we introduce a three-stage method for giving hints to the student without revealing the correct solution of an example. We categorize mistakes into (i) syntactic mistakes, (ii) unexpected but syntactically correct input, and (iii) semantic mistakes, describe mathematical definitions of these mistakes, and show how to compute hints from these definitions.
Tasks
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07847v1
PDF	http://arxiv.org/pdf/1607.07847v1.pdf
PWC	https://paperswithcode.com/paper/technical-report-giving-hints-for-logic
Repo
Framework

An Efficient Large-scale Semi-supervised Multi-label Classifier Capable of Handling Missing labels


Title	An Efficient Large-scale Semi-supervised Multi-label Classifier Capable of Handling Missing labels
Authors	Amirhossein Akbarnejad, Mahdieh Soleymani Baghshah
Abstract	Multi-label classification has received considerable interest in recent years. Multi-label classifiers have to address many problems including: handling large-scale datasets with many instances and a large set of labels, compensating missing label assignments in the training set, considering correlations between labels, as well as exploiting unlabeled data to improve prediction performance. To tackle datasets with a large set of labels, embedding-based methods have been proposed which seek to represent the label assignments in a low-dimensional space. Many state-of-the-art embedding-based methods use a linear dimensionality reduction to represent the label assignments in a low-dimensional space. However, by doing so, these methods actually neglect the tail labels - labels that are infrequently assigned to instances. We propose an embedding-based method that non-linearly embeds the label vectors using an stochastic approach, thereby predicting the tail labels more accurately. Moreover, the proposed method have excellent mechanisms for handling missing labels, dealing with large-scale datasets, as well as exploiting unlabeled data. With the best of our knowledge, our proposed method is the first multi-label classifier that simultaneously addresses all of the mentioned challenges. Experiments on real-world datasets show that our method outperforms stateof-the-art multi-label classifiers by a large margin, in terms of prediction performance, as well as training time.
Tasks	Dimensionality Reduction, Multi-Label Classification
Published	2016-06-18
URL	http://arxiv.org/abs/1606.05725v1
PDF	http://arxiv.org/pdf/1606.05725v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-large-scale-semi-supervised
Repo
Framework