May 6, 2019

3447 words 17 mins read

Paper Group ANR 177

Learning Fast Sparsifying Transforms. An Information Extraction Approach to Prescreen Heart Failure Patients for Clinical Trials. OpenTripPlanner, OpenStreetMap, General Transit Feed Specification: Tools for Disaster Relief and Recovery. A Novel Progressive Multi-label Classifier for Classincremental Data. Minimax Lower Bounds for Kronecker-Structu …

Learning Fast Sparsifying Transforms


Title	Learning Fast Sparsifying Transforms
Authors	Cristian Rusu, John Thompson
Abstract	Given a dataset, the task of learning a transform that allows sparse representations of the data bears the name of dictionary learning. In many applications, these learned dictionaries represent the data much better than the static well-known transforms (Fourier, Hadamard etc.). The main downside of learned transforms is that they lack structure and therefore they are not computationally efficient, unlike their classical counterparts. These posse several difficulties especially when using power limited hardware such as mobile devices, therefore discouraging the application of sparsity techniques in such scenarios. In this paper we construct orthogonal and non-orthogonal dictionaries that are factorized as a product of a few basic transformations. In the orthogonal case, we solve exactly the dictionary update problem for one basic transformation, which can be viewed as a generalized Givens rotation, and then propose to construct orthogonal dictionaries that are a product of these transformations, guaranteeing their fast manipulation. We also propose a method to construct fast square but non-orthogonal dictionaries that are factorized as a product of few transforms that can be viewed as a further generalization of Givens rotations to the non-orthogonal setting. We show how the proposed transforms can balance very well data representation performance and computational complexity. We also compare with classical fast and learned general and orthogonal transforms.
Tasks	Dictionary Learning
Published	2016-11-24
URL	http://arxiv.org/abs/1611.08230v2
PDF	http://arxiv.org/pdf/1611.08230v2.pdf
PWC	https://paperswithcode.com/paper/learning-fast-sparsifying-transforms
Repo
Framework

An Information Extraction Approach to Prescreen Heart Failure Patients for Clinical Trials


Title	An Information Extraction Approach to Prescreen Heart Failure Patients for Clinical Trials
Authors	Abhishek Kalyan Adupa, Ravi Prakash Garg, Jessica Corona-Cox, Sanjiv. J. Shah, Siddhartha R. Jonnalagadda
Abstract	To reduce the large amount of time spent screening, identifying, and recruiting patients into clinical trials, we need prescreening systems that are able to automate the data extraction and decision-making tasks that are typically relegated to clinical research study coordinators. However, a major obstacle is the vast amount of patient data available as unstructured free-form text in electronic health records. Here we propose an information extraction-based approach that first automatically converts unstructured text into a structured form. The structured data are then compared against a list of eligibility criteria using a rule-based system to determine which patients qualify for enrollment in a heart failure clinical trial. We show that we can achieve highly accurate results, with recall and precision values of 0.95 and 0.86, respectively. Our system allowed us to significantly reduce the time needed for prescreening patients from a few weeks to a few minutes. Our open-source information extraction modules are available for researchers and could be tested and validated in other cardiovascular trials. An approach such as the one we demonstrate here may decrease costs and expedite clinical trials, and could enhance the reproducibility of trials across institutions and populations.
Tasks	Decision Making
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01594v1
PDF	http://arxiv.org/pdf/1609.01594v1.pdf
PWC	https://paperswithcode.com/paper/an-information-extraction-approach-to
Repo
Framework

OpenTripPlanner, OpenStreetMap, General Transit Feed Specification: Tools for Disaster Relief and Recovery


Title	OpenTripPlanner, OpenStreetMap, General Transit Feed Specification: Tools for Disaster Relief and Recovery
Authors	Chelcie Narboneta, Kardi Teknomo
Abstract	Open Trip Planner was identified as the most promising open source multi-modal trip planning software. Open Street Map, which provides mapping data to Open Trip Planner, is one of the most well-known open source international repository of geographic data. General Transit Feed Specification, which provides transportation data to Open Trip Planner, has been the standard for describing transit systems and platform for numerous applications. Together, when used to implement an instance of Open Trip Planner, these software has been helping in traffic decongestion all over the world by assisting commuters to shift from using private transportation modes to public ones. Their potential however goes beyond providing multi-modal public transportation routes. This paper aims to first discuss the researchers’ experience in implementing a public transportation route planner for the purpose of traffic decongestion.The researchers would examine the prospective of using the system for disaster preparedness and recovery and concrete ways on how to realize them.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01472v1
PDF	http://arxiv.org/pdf/1609.01472v1.pdf
PWC	https://paperswithcode.com/paper/opentripplanner-openstreetmap-general-transit
Repo
Framework

A Novel Progressive Multi-label Classifier for Classincremental Data


Title	A Novel Progressive Multi-label Classifier for Classincremental Data
Authors	Mihika Dave, Sahil Tapiawala, Meng Joo Er, Rajasekar Venkatesan
Abstract	In this paper, a progressive learning algorithm for multi-label classification to learn new labels while retaining the knowledge of previous labels is designed. New output neurons corresponding to new labels are added and the neural network connections and parameters are automatically restructured as if the label has been introduced from the beginning. This work is the first of the kind in multi-label classifier for class-incremental learning. It is useful for real-world applications such as robotics where streaming data are available and the number of labels is often unknown. Based on the Extreme Learning Machine framework, a novel universal classifier with plug and play capabilities for progressive multi-label classification is developed. Experimental results on various benchmark synthetic and real datasets validate the efficiency and effectiveness of our proposed algorithm.
Tasks	Multi-Label Classification
Published	2016-09-23
URL	http://arxiv.org/abs/1609.07215v1
PDF	http://arxiv.org/pdf/1609.07215v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-progressive-multi-label-classifier
Repo
Framework

Minimax Lower Bounds for Kronecker-Structured Dictionary Learning


Title	Minimax Lower Bounds for Kronecker-Structured Dictionary Learning
Authors	Zahra Shakeri, Waheed U. Bajwa, Anand D. Sarwate
Abstract	Dictionary learning is the problem of estimating the collection of atomic elements that provide a sparse representation of measured/collected signals or data. This paper finds fundamental limits on the sample complexity of estimating dictionaries for tensor data by proving a lower bound on the minimax risk. This lower bound depends on the dimensions of the tensor and parameters of the generative model. The focus of this paper is on second-order tensor data, with the underlying dictionaries constructed by taking the Kronecker product of two smaller dictionaries and the observed data generated by sparse linear combinations of dictionary atoms observed through white Gaussian noise. In this regard, the paper provides a general lower bound on the minimax risk and also adapts the proof techniques for equivalent results using sparse and Gaussian coefficient models. The reported results suggest that the sample complexity of dictionary learning for tensor data can be significantly lower than that for unstructured data.
Tasks	Dictionary Learning
Published	2016-05-17
URL	http://arxiv.org/abs/1605.05284v1
PDF	http://arxiv.org/pdf/1605.05284v1.pdf
PWC	https://paperswithcode.com/paper/minimax-lower-bounds-for-kronecker-structured
Repo
Framework

Adaptive Down-Sampling and Dimension Reduction in Time Elastic Kernel Machines for Efficient Recognition of Isolated Gestures


Title	Adaptive Down-Sampling and Dimension Reduction in Time Elastic Kernel Machines for Efficient Recognition of Isolated Gestures
Authors	Pierre-François Marteau, Sylvie Gibet, Clément Reverdy
Abstract	In the scope of gestural action recognition, the size of the feature vector representing movements is in general quite large especially when full body movements are considered. Furthermore, this feature vector evolves during the movement performance so that a complete movement is fully represented by a matrix M of size DxT , whose element M i, j represents the value of feature i at timestamps j. Many studies have addressed dimensionality reduction considering only the size of the feature vector lying in R D to reduce both the variability of gestural sequences expressed in the reduced space, and the computational complexity of their processing. In return, very few of these methods have explicitly addressed the dimensionality reduction along the time axis. Yet this is a major issue when considering the use of elastic distances which are characterized by a quadratic complexity along the time axis. We present in this paper an evaluation of straightforward approaches aiming at reducing the dimensionality of the matrix M for each movement, leading to consider both the dimensionality reduction of the feature vector as well as its reduction along the time axis. The dimensionality reduction of the feature vector is achieved by selecting remarkable joints in the skeleton performing the movement, basically the extremities of the articulatory chains composing the skeleton. The temporal dimen-sionality reduction is achieved using either a regular or adaptive down-sampling that seeks to minimize the reconstruction error of the movements. Elastic and Euclidean kernels are then compared through support vector machine learning. Two data sets 1 that are widely referenced in the domain of human gesture recognition, and quite distinctive in terms of quality of motion capture, are used for the experimental assessment of the proposed approaches. On these data sets we experimentally show that it is feasible, and possibly desirable, to significantly reduce simultaneously the size of the feature vector and the number of skeleton frames to represent body movements while maintaining a very good recognition rate. The method proves to give satisfactory results at a level currently reached by state-of-the-art methods on these data sets. We experimentally show that the computational complexity reduction that is obtained makes this approach eligible for real-time applications.
Tasks	Dimensionality Reduction, Gesture Recognition, Motion Capture, Temporal Action Localization
Published	2016-11-23
URL	http://arxiv.org/abs/1611.07781v1
PDF	http://arxiv.org/pdf/1611.07781v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-down-sampling-and-dimension
Repo
Framework

Image Captioning with Semantic Attention


Title	Image Captioning with Semantic Attention
Authors	Quanzeng You, Hailin Jin, Zhaowen Wang, Chen Fang, Jiebo Luo
Abstract	Automatically generating a natural language description of an image has attracted interests recently both because of its importance in practical applications and because it connects two major artificial intelligence fields: computer vision and natural language processing. Existing approaches are either top-down, which start from a gist of an image and convert it into words, or bottom-up, which come up with words describing various aspects of an image and then combine them. In this paper, we propose a new algorithm that combines both approaches through a model of semantic attention. Our algorithm learns to selectively attend to semantic concept proposals and fuse them into hidden states and outputs of recurrent neural networks. The selection and fusion form a feedback connecting the top-down and bottom-up computation. We evaluate our algorithm on two public benchmarks: Microsoft COCO and Flickr30K. Experimental results show that our algorithm significantly outperforms the state-of-the-art approaches consistently across different evaluation metrics.
Tasks	Image Captioning
Published	2016-03-12
URL	http://arxiv.org/abs/1603.03925v1
PDF	http://arxiv.org/pdf/1603.03925v1.pdf
PWC	https://paperswithcode.com/paper/image-captioning-with-semantic-attention
Repo
Framework

Distant Supervision for Relation Extraction beyond the Sentence Boundary


Title	Distant Supervision for Relation Extraction beyond the Sentence Boundary
Authors	Chris Quirk, Hoifung Poon
Abstract	The growing demand for structured knowledge has led to great interest in relation extraction, especially in cases with limited supervision. However, existing distance supervision approaches only extract relations expressed in single sentences. In general, cross-sentence relation extraction is under-explored, even in the supervised-learning setting. In this paper, we propose the first approach for applying distant supervision to cross- sentence relation extraction. At the core of our approach is a graph representation that can incorporate both standard dependencies and discourse relations, thus providing a unifying way to model relations within and across sentences. We extract features from multiple paths in this graph, increasing accuracy and robustness when confronted with linguistic variation and analysis error. Experiments on an important extraction task for precision medicine show that our approach can learn an accurate cross-sentence extractor, using only a small existing knowledge base and unlabeled text from biomedical research articles. Compared to the existing distant supervision paradigm, our approach extracted twice as many relations at similar precision, thus demonstrating the prevalence of cross-sentence relations and the promise of our approach.
Tasks	Relation Extraction
Published	2016-09-15
URL	http://arxiv.org/abs/1609.04873v3
PDF	http://arxiv.org/pdf/1609.04873v3.pdf
PWC	https://paperswithcode.com/paper/distant-supervision-for-relation-extraction-1
Repo
Framework

Multiple Instance Learning Convolutional Neural Networks for Object Recognition


Title	Multiple Instance Learning Convolutional Neural Networks for Object Recognition
Authors	Miao Sun, Tony X. Han, Ming-Chang Liu, Ahmad Khodayari-Rostamabad
Abstract	Convolutional Neural Networks (CNN) have demon- strated its successful applications in computer vision, speech recognition, and natural language processing. For object recog- nition, CNNs might be limited by its strict label requirement and an implicit assumption that images are supposed to be target- object-dominated for optimal solutions. However, the labeling procedure, necessitating laying out the locations of target ob- jects, is very tedious, making high-quality large-scale dataset prohibitively expensive. Data augmentation schemes are widely used when deep networks suffer the insufficient training data problem. All the images produced through data augmentation share the same label, which may be problematic since not all data augmentation methods are label-preserving. In this paper, we propose a weakly supervised CNN framework named Multiple Instance Learning Convolutional Neural Networks (MILCNN) to solve this problem. We apply MILCNN framework to object recognition and report state-of-the-art performance on three benchmark datasets: CIFAR10, CIFAR100 and ILSVRC2015 classification dataset.
Tasks	Data Augmentation, Multiple Instance Learning, Object Recognition, Speech Recognition
Published	2016-10-11
URL	http://arxiv.org/abs/1610.03155v1
PDF	http://arxiv.org/pdf/1610.03155v1.pdf
PWC	https://paperswithcode.com/paper/multiple-instance-learning-convolutional
Repo
Framework

Scalability in Neural Control of Musculoskeletal Robots


Title	Scalability in Neural Control of Musculoskeletal Robots
Authors	Christoph Richter, Sören Jentzsch, Rafael Hostettler, Jesús A. Garrido, Eduardo Ros, Alois C. Knoll, Florian Röhrbein, Patrick van der Smagt, Jörg Conradt
Abstract	Anthropomimetic robots are robots that sense, behave, interact and feel like humans. By this definition, anthropomimetic robots require human-like physical hardware and actuation, but also brain-like control and sensing. The most self-evident realization to meet those requirements would be a human-like musculoskeletal robot with a brain-like neural controller. While both musculoskeletal robotic hardware and neural control software have existed for decades, a scalable approach that could be used to build and control an anthropomimetic human-scale robot has not been demonstrated yet. Combining Myorobotics, a framework for musculoskeletal robot development, with SpiNNaker, a neuromorphic computing platform, we present the proof-of-principle of a system that can scale to dozens of neurally-controlled, physically compliant joints. At its core, it implements a closed-loop cerebellar model which provides real-time low-level neural control at minimal power consumption and maximal extensibility: higher-order (e.g., cortical) neural networks and neuromorphic sensors like silicon-retinae or -cochleae can naturally be incorporated.
Tasks
Published	2016-01-19
URL	http://arxiv.org/abs/1601.04862v1
PDF	http://arxiv.org/pdf/1601.04862v1.pdf
PWC	https://paperswithcode.com/paper/scalability-in-neural-control-of
Repo
Framework

Adaptive Nonnegative Matrix Factorization and Measure Comparisons for Recommender Systems


Title	Adaptive Nonnegative Matrix Factorization and Measure Comparisons for Recommender Systems
Authors	Gianna M. Del Corso, Francesco Romani
Abstract	The Nonnegative Matrix Factorization (NMF) of the rating matrix has shown to be an effective method to tackle the recommendation problem. In this paper we propose new methods based on the NMF of the rating matrix and we compare them with some classical algorithms such as the SVD and the regularized and unregularized non-negative matrix factorization approach. In particular a new algorithm is obtained changing adaptively the function to be minimized at each step, realizing a sort of dynamic prior strategy. Another algorithm is obtained modifying the function to be minimized in the NMF formulation by enforcing the reconstruction of the unknown ratings toward a prior term. We then combine different methods obtaining two mixed strategies which turn out to be very effective in the reconstruction of missing observations. We perform a thoughtful comparison of different methods on the basis of several evaluation measures. We consider in particular rating, classification and ranking measures showing that the algorithm obtaining the best score for a given measure is in general the best also when different measures are considered, lowering the interest in designing specific evaluation measures. The algorithms have been tested on different datasets, in particular the 1M, and 10M MovieLens datasets containing ratings on movies, the Jester dataset with ranting on jokes and Amazon Fine Foods dataset with ratings on foods. The comparison of the different algorithms, shows the good performance of methods employing both an explicit and an implicit regularization scheme. Moreover we can get a boost by mixed strategies combining a fast method with a more accurate one.
Tasks	Recommendation Systems
Published	2016-07-26
URL	https://arxiv.org/abs/1607.07607v3
PDF	https://arxiv.org/pdf/1607.07607v3.pdf
PWC	https://paperswithcode.com/paper/adaptive-nonnegative-matrix-factorization-and
Repo
Framework

Neuromorphic Robot Dream


Title	Neuromorphic Robot Dream
Authors	Alexander Tchitchigin, Max Talanov, Larisa Safina, Manuel Mazzara
Abstract	In this paper we present the next step in our approach to neurobiologically plausible implementation of emotional reactions and behaviors for real-time autonomous robotic systems. The working metaphor we use is the “day” and the “night” phases of mammalian life. During the “day phase” a robotic system stores the inbound information and is controlled by a light-weight rule-based system in real time. In contrast to that, during the “night phase” information that has been stored is transferred to a supercomputing system to update the realistic neural network: emotional and behavioral strategies.
Tasks
Published	2016-07-27
URL	http://arxiv.org/abs/1607.08131v1
PDF	http://arxiv.org/pdf/1607.08131v1.pdf
PWC	https://paperswithcode.com/paper/neuromorphic-robot-dream
Repo
Framework

Online Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems


Title	Online Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems
Authors	Aryan Mokhtari, Shahin Shahrampour, Ali Jadbabaie, Alejandro Ribeiro
Abstract	In this paper, we address tracking of a time-varying parameter with unknown dynamics. We formalize the problem as an instance of online optimization in a dynamic setting. Using online gradient descent, we propose a method that sequentially predicts the value of the parameter and in turn suffers a loss. The objective is to minimize the accumulation of losses over the time horizon, a notion that is termed dynamic regret. While existing methods focus on convex loss functions, we consider strongly convex functions so as to provide better guarantees of performance. We derive a regret bound that captures the path-length of the time-varying parameter, defined in terms of the distance between its consecutive values. In other words, the bound represents the natural connection of tracking quality to the rate of change of the parameter. We provide numerical experiments to complement our theoretical findings.
Tasks
Published	2016-03-16
URL	http://arxiv.org/abs/1603.04954v1
PDF	http://arxiv.org/pdf/1603.04954v1.pdf
PWC	https://paperswithcode.com/paper/online-optimization-in-dynamic-environments
Repo
Framework

Decoding the Encoding of Functional Brain Networks: an fMRI Classification Comparison of Non-negative Matrix Factorization (NMF), Independent Component Analysis (ICA), and Sparse Coding Algorithms


Title	Decoding the Encoding of Functional Brain Networks: an fMRI Classification Comparison of Non-negative Matrix Factorization (NMF), Independent Component Analysis (ICA), and Sparse Coding Algorithms
Authors	Jianwen Xie, Pamela K. Douglas, Ying Nian Wu, Arthur L. Brody, Ariana E. Anderson
Abstract	Brain networks in fMRI are typically identified using spatial independent component analysis (ICA), yet mathematical constraints such as sparse coding and positivity both provide alternate biologically-plausible frameworks for generating brain networks. Non-negative Matrix Factorization (NMF) would suppress negative BOLD signal by enforcing positivity. Spatial sparse coding algorithms ($L1$ Regularized Learning and K-SVD) would impose local specialization and a discouragement of multitasking, where the total observed activity in a single voxel originates from a restricted number of possible brain networks. The assumptions of independence, positivity, and sparsity to encode task-related brain networks are compared; the resulting brain networks for different constraints are used as basis functions to encode the observed functional activity at a given time point. These encodings are decoded using machine learning to compare both the algorithms and their assumptions, using the time series weights to predict whether a subject is viewing a video, listening to an audio cue, or at rest, in 304 fMRI scans from 51 subjects. For classifying cognitive activity, the sparse coding algorithm of $L1$ Regularized Learning consistently outperformed 4 variations of ICA across different numbers of networks and noise levels (p$<$0.001). The NMF algorithms, which suppressed negative BOLD signal, had the poorest accuracy. Within each algorithm, encodings using sparser spatial networks (containing more zero-valued voxels) had higher classification accuracy (p$<$0.001). The success of sparse coding algorithms may suggest that algorithms which enforce sparse coding, discourage multitasking, and promote local specialization may capture better the underlying source processes than those which allow inexhaustible local processes such as ICA.
Tasks	Time Series
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00435v1
PDF	http://arxiv.org/pdf/1607.00435v1.pdf
PWC	https://paperswithcode.com/paper/decoding-the-encoding-of-functional-brain
Repo
Framework

Factorized Bilinear Models for Image Recognition


Title	Factorized Bilinear Models for Image Recognition
Authors	Yanghao Li, Naiyan Wang, Jiaying Liu, Xiaodi Hou
Abstract	Although Deep Convolutional Neural Networks (CNNs) have liberated their power in various computer vision tasks, the most important components of CNN, convolutional layers and fully connected layers, are still limited to linear transformations. In this paper, we propose a novel Factorized Bilinear (FB) layer to model the pairwise feature interactions by considering the quadratic terms in the transformations. Compared with existing methods that tried to incorporate complex non-linearity structures into CNNs, the factorized parameterization makes our FB layer only require a linear increase of parameters and affordable computational cost. To further reduce the risk of overfitting of the FB layer, a specific remedy called DropFactor is devised during the training process. We also analyze the connection between FB layer and some existing models, and show FB layer is a generalization to them. Finally, we validate the effectiveness of FB layer on several widely adopted datasets including CIFAR-10, CIFAR-100 and ImageNet, and demonstrate superior results compared with various state-of-the-art deep models.
Tasks
Published	2016-11-17
URL	http://arxiv.org/abs/1611.05709v2
PDF	http://arxiv.org/pdf/1611.05709v2.pdf
PWC	https://paperswithcode.com/paper/factorized-bilinear-models-for-image
Repo
Framework