May 6, 2019

2888 words 14 mins read

Paper Group ANR 283

Precise neural network computation with imprecise analog devices. Context-Aware Adaptive Framework for e-Health Monitoring. Automatic Selection of Context Configurations for Improved Class-Specific Word Representations. Classification and Learning-to-rank Approaches for Cross-Device Matching at CIKM Cup 2016. Two-Level Structural Sparsity Regulariz …

Precise neural network computation with imprecise analog devices


Title	Precise neural network computation with imprecise analog devices
Authors	Jonathan Binas, Daniel Neil, Giacomo Indiveri, Shih-Chii Liu, Michael Pfeiffer
Abstract	The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency. Nevertheless, such implementations have been largely supplanted by digital designs, partly because of device mismatch effects due to material and fabrication imperfections. We propose a framework that exploits the power of deep learning to compensate for this mismatch by incorporating the measured device variations as constraints in the neural network training process. This eliminates the need for mismatch minimization strategies and allows circuit complexity and power-consumption to be reduced to a minimum. Our results, based on large-scale simulations as well as a prototype VLSI chip implementation indicate a processing efficiency comparable to current state-of-art digital implementations. This method is suitable for future technology based on nanodevices with large variability, such as memristive arrays.
Tasks
Published	2016-06-23
URL	https://arxiv.org/abs/1606.07786v2
PDF	https://arxiv.org/pdf/1606.07786v2.pdf
PWC	https://paperswithcode.com/paper/precise-deep-neural-network-computation-on
Repo
Framework

Context-Aware Adaptive Framework for e-Health Monitoring


Title	Context-Aware Adaptive Framework for e-Health Monitoring
Authors	Haider Mshali, Tayeb Lemlouma, Damien Magoni
Abstract	For improving e-health services, we propose a context-aware framework to monitor the activities of daily living of dependent persons. We define a strategy for generating long-term realistic scenarios and a framework containing an adaptive monitoring algorithm based on three approaches for optimizing resource usage. The used approaches provide a deep knowledge about the person’s context by considering: the person’s profile, the activities and the relationships between activities. We evaluate the performances of our framework and show its adaptability and significant reduction in network, energy and processing usage over a traditional monitoring implementation.
Tasks
Published	2016-05-10
URL	http://arxiv.org/abs/1605.03035v1
PDF	http://arxiv.org/pdf/1605.03035v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-adaptive-framework-for-e-health
Repo
Framework

Automatic Selection of Context Configurations for Improved Class-Specific Word Representations


Title	Automatic Selection of Context Configurations for Improved Class-Specific Word Representations
Authors	Ivan Vulić, Roy Schwartz, Ari Rappoport, Roi Reichart, Anna Korhonen
Abstract	This paper is concerned with identifying contexts useful for training word representation models for different word classes such as adjectives (A), verbs (V), and nouns (N). We introduce a simple yet effective framework for an automatic selection of class-specific context configurations. We construct a context configuration space based on universal dependency relations between words, and efficiently search this space with an adapted beam search algorithm. In word similarity tasks for each word class, we show that our framework is both effective and efficient. Particularly, it improves the Spearman’s rho correlation with human scores on SimLex-999 over the best previously proposed class-specific contexts by 6 (A), 6 (V) and 5 (N) rho points. With our selected context configurations, we train on only 14% (A), 26.2% (V), and 33.6% (N) of all dependency-based contexts, resulting in a reduced training time. Our results generalise: we show that the configurations our algorithm learns for one English training setup outperform previously proposed context types in another training setup for English. Moreover, basing the configuration space on universal dependencies, it is possible to transfer the learned configurations to German and Italian. We also demonstrate improved per-class results over other context types in these two languages.
Tasks
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05528v3
PDF	http://arxiv.org/pdf/1608.05528v3.pdf
PWC	https://paperswithcode.com/paper/automatic-selection-of-context-configurations
Repo
Framework

Classification and Learning-to-rank Approaches for Cross-Device Matching at CIKM Cup 2016


Title	Classification and Learning-to-rank Approaches for Cross-Device Matching at CIKM Cup 2016
Authors	Nam Khanh Tran
Abstract	In this paper, we propose two methods for tackling the problem of cross-device matching for online advertising at CIKM Cup 2016. The first method considers the matching problem as a binary classification task and solve it by utilizing ensemble learning techniques. The second method defines the matching problem as a ranking task and effectively solve it with using learning-to-rank algorithms. The results show that the proposed methods obtain promising results, in which the ranking-based method outperforms the classification-based method for the task.
Tasks	Learning-To-Rank
Published	2016-12-20
URL	http://arxiv.org/abs/1612.07117v1
PDF	http://arxiv.org/pdf/1612.07117v1.pdf
PWC	https://paperswithcode.com/paper/classification-and-learning-to-rank
Repo
Framework

Two-Level Structural Sparsity Regularization for Identifying Lattices and Defects in Noisy Images


Title	Two-Level Structural Sparsity Regularization for Identifying Lattices and Defects in Noisy Images
Authors	Xin Li, Alex Belianinov, Ondrej Dyck, Stephen Jesse, Chiwoo Park
Abstract	This paper presents a regularized regression model with a two-level structural sparsity penalty applied to locate individual atoms in a noisy scanning transmission electron microscopy image (STEM). In crystals, the locations of atoms is symmetric, condensed into a few lattice groups. Therefore, by identifying the underlying lattice in a given image, individual atoms can be accurately located. We propose to formulate the identification of the lattice groups as a sparse group selection problem. Furthermore, real atomic scale images contain defects and vacancies, so atomic identification based solely on a lattice group may result in false positives and false negatives. To minimize error, model includes an individual sparsity regularization in addition to the group sparsity for a within-group selection, which results in a regression model with a two-level sparsity regularization. We propose a modification of the group orthogonal matching pursuit (gOMP) algorithm with a thresholding step to solve the atom finding problem. The convergence and statistical analyses of the proposed algorithm are presented. The proposed algorithm is also evaluated through numerical experiments with simulated images. The applicability of the algorithm on determination of atom structures and identification of imaging distortions and atomic defects was demonstrated using three real STEM images. We believe this is an important step toward automatic phase identification and assignment with the advent of genomic databases for materials.
Tasks
Published	2016-11-24
URL	http://arxiv.org/abs/1611.08280v4
PDF	http://arxiv.org/pdf/1611.08280v4.pdf
PWC	https://paperswithcode.com/paper/two-level-structural-sparsity-regularization
Repo
Framework

Reading Between the Pixels: Photographic Steganography for Camera Display Messaging


Title	Reading Between the Pixels: Photographic Steganography for Camera Display Messaging
Authors	Eric Wengrowski, Kristin Dana, Marco Gruteser, Narayan Mandayam
Abstract	We exploit human color metamers to send light-modulated messages less visible to the human eye, but recoverable by cameras. These messages are a key component to camera-display messaging, such as handheld smartphones capturing information from electronic signage. Each color pixel in the display image is modified by a particular color gradient vector. The challenge is to find the color gradient that maximizes camera response, while minimizing human response. The mismatch in human spectral and camera sensitivity curves creates an opportunity for hidden messaging. Our approach does not require knowledge of these sensitivity curves, instead we employ a data-driven method. We learn an ellipsoidal partitioning of the six-dimensional space of colors and color gradients. This partitioning creates metamer sets defined by the base color at the display pixel and the color gradient direction for message encoding. We sample from the resulting metamer sets to find color steps for each base color to embed a binary message into an arbitrary image with reduced visible artifacts. Unlike previous methods that rely on visually obtrusive intensity modulation, we embed with color so that the message is more hidden. Ordinary displays and cameras are used without the need for expensive LEDs or high speed devices. The primary contribution of this work is a framework to map the pixels in an arbitrary image to a metamer pair for steganographic photo messaging.
Tasks
Published	2016-04-06
URL	http://arxiv.org/abs/1604.01720v1
PDF	http://arxiv.org/pdf/1604.01720v1.pdf
PWC	https://paperswithcode.com/paper/reading-between-the-pixels-photographic
Repo
Framework


Title	Error concealment by means of motion refinement and regularized Bregman divergence
Authors	Alessandra M. Coelho, Vania V. Estrela, Felipe P. do Carmo, Sandro R. Fernandes
Abstract	This work addresses the problem of error concealment in video transmission systems over noisy channels employing Bregman divergences along with regularization. Error concealment intends to improve the effects of disturbances at the reception due to bit-errors or cell loss in packet networks. Bregman regularization gives accurate answers after just some iterations with fast convergence, better accuracy, and stability. This technique has an adaptive nature: the regularization functional is updated according to Bregman functions that change from iteration to iteration according to the nature of the neighborhood under study at iteration n. Numerical experiments show that high-quality regularization parameter estimates can be obtained. The convergence is sped up while turning the regularization parameter estimation less empiric, and more automatic.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03268v1
PDF	http://arxiv.org/pdf/1611.03268v1.pdf
PWC	https://paperswithcode.com/paper/error-concealment-by-means-of-motion
Repo
Framework

Testing Ising Models


Title	Testing Ising Models
Authors	Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath
Abstract	Given samples from an unknown multivariate distribution $p$, is it possible to distinguish whether $p$ is the product of its marginals versus $p$ being far from every product distribution? Similarly, is it possible to distinguish whether $p$ equals a given distribution $q$ versus $p$ and $q$ being far from each other? These problems of testing independence and goodness-of-fit have received enormous attention in statistics, information theory, and theoretical computer science, with sample-optimal algorithms known in several interesting regimes of parameters. Unfortunately, it has also been understood that these problems become intractable in large dimensions, necessitating exponential sample complexity. Motivated by the exponential lower bounds for general distributions as well as the ubiquity of Markov Random Fields (MRFs) in the modeling of high-dimensional distributions, we initiate the study of distribution testing on structured multivariate distributions, and in particular the prototypical example of MRFs: the Ising Model. We demonstrate that, in this structured setting, we can avoid the curse of dimensionality, obtaining sample and time efficient testers for independence and goodness-of-fit. One of the key technical challenges we face along the way is bounding the variance of functions of the Ising model.
Tasks
Published	2016-12-09
URL	https://arxiv.org/abs/1612.03147v6
PDF	https://arxiv.org/pdf/1612.03147v6.pdf
PWC	https://paperswithcode.com/paper/testing-ising-models
Repo
Framework

Principal Component Projection Without Principal Component Analysis


Title	Principal Component Projection Without Principal Component Analysis
Authors	Roy Frostig, Cameron Musco, Christopher Musco, Aaron Sidford
Abstract	We show how to efficiently project a vector onto the top principal components of a matrix, without explicitly computing these components. Specifically, we introduce an iterative algorithm that provably computes the projection using few calls to any black-box routine for ridge regression. By avoiding explicit principal component analysis (PCA), our algorithm is the first with no runtime dependence on the number of top principal components. We show that it can be used to give a fast iterative method for the popular principal component regression problem, giving the first major runtime improvement over the naive method of combining PCA with regression. To achieve our results, we first observe that ridge regression can be used to obtain a “smooth projection” onto the top principal components. We then sharpen this approximation to true projection using a low-degree polynomial approximation to the matrix step function. Step function approximation is a topic of long-term interest in scientific computing. We extend prior theory by constructing polynomials with simple iterative structure and rigorously analyzing their behavior under limited precision.
Tasks
Published	2016-02-22
URL	https://arxiv.org/abs/1602.06872v2
PDF	https://arxiv.org/pdf/1602.06872v2.pdf
PWC	https://paperswithcode.com/paper/principal-component-projection-without
Repo
Framework

Spikes as regularizers


Title	Spikes as regularizers
Authors	Anders Søgaard
Abstract	We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and activation offsets relative to previous activity. We regularize updates proportionally to item-level confidence and weight-specific support, loosely inspired by the observation from neurophysiology that high spike rates are sometimes accompanied by low temporal precision. Our experiments suggest that the new learning algorithm SPIRAL is more robust and less prone to overfitting than both the averaged perceptron and AROW.
Tasks
Published	2016-11-18
URL	http://arxiv.org/abs/1611.06245v1
PDF	http://arxiv.org/pdf/1611.06245v1.pdf
PWC	https://paperswithcode.com/paper/spikes-as-regularizers
Repo
Framework

QuotationFinder - Searching for Quotations and Allusions in Greek and Latin Texts and Establishing the Degree to Which a Quotation or Allusion Matches Its Source


Title	QuotationFinder - Searching for Quotations and Allusions in Greek and Latin Texts and Establishing the Degree to Which a Quotation or Allusion Matches Its Source
Authors	Luc Herren
Abstract	The software programs generally used with the TLG (Thesaurus Linguae Graecae) and the CLCLT (CETEDOC Library of Christian Latin Texts) CD-ROMs are not well suited for finding quotations and allusions. QuotationFinder uses more sophisticated criteria as it ranks search results based on how closely they match the source text, listing search results with literal quotations first and loose verbal parallels last.
Tasks
Published	2016-02-28
URL	http://arxiv.org/abs/1602.08657v2
PDF	http://arxiv.org/pdf/1602.08657v2.pdf
PWC	https://paperswithcode.com/paper/quotationfinder-searching-for-quotations-and
Repo
Framework

A fractal dimension based optimal wavelet packet analysis technique for classification of meningioma brain tumours


Title	A fractal dimension based optimal wavelet packet analysis technique for classification of meningioma brain tumours
Authors	Omar S. Al-Kadi
Abstract	With the heterogeneous nature of tissue texture, using a single resolution approach for optimum classification might not suffice. In contrast, a multiresolution wavelet packet analysis can decompose the input signal into a set of frequency subbands giving the opportunity to characterise the texture at the appropriate frequency channel. An adaptive best bases algorithm for optimal bases selection for meningioma histopathological images is proposed, via applying the fractal dimension (FD) as the bases selection criterion in a tree-structured manner. Thereby, the most significant subband that better identifies texture discontinuities will only be chosen for further decomposition, and its fractal signature would represent the extracted feature vector for classification. The best basis selection using the FD outperformed the energy based selection approaches, achieving an overall classification accuracy of 91.25% as compared to 83.44% and 73.75% for the co-occurrence matrix and energy texture signatures; respectively.
Tasks
Published	2016-01-02
URL	http://arxiv.org/abs/1601.00211v1
PDF	http://arxiv.org/pdf/1601.00211v1.pdf
PWC	https://paperswithcode.com/paper/a-fractal-dimension-based-optimal-wavelet
Repo
Framework

Robust Unsupervised Transient Detection With Invariant Representation based on the Scattering Network


Title	Robust Unsupervised Transient Detection With Invariant Representation based on the Scattering Network
Authors	Randall Balestriero, Behnaam Aazhang
Abstract	We present a sparse and invariant representation with low asymptotic complexity for robust unsupervised transient and onset zone detection in noisy environments. This unsupervised approach is based on wavelet transforms and leverages the scattering network from Mallat et al. by deriving frequency invariance. This frequency invariance is a key concept to enforce robust representations of transients in presence of possible frequency shifts and perturbations occurring in the original signal. Implementation details as well as complexity analysis are provided in addition of the theoretical framework and the invariance properties. In this work, our primary application consists of predicting the onset of seizure in epileptic patients from subdural recordings as well as detecting inter-ictal spikes.
Tasks
Published	2016-11-23
URL	http://arxiv.org/abs/1611.07850v1
PDF	http://arxiv.org/pdf/1611.07850v1.pdf
PWC	https://paperswithcode.com/paper/robust-unsupervised-transient-detection-with
Repo
Framework

DeMIAN: Deep Modality Invariant Adversarial Network


Title	DeMIAN: Deep Modality Invariant Adversarial Network
Authors	Kuniaki Saito, Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada
Abstract	Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and apply it to the testing of the text features in the representations. Existing multi-modal representation learning methods mainly aim to extract rich information from paired samples and train a classifier by the corresponding labels; however, collecting paired samples and their labels simultaneously involves high labor costs. Addressing paired modal samples without their labels and single modal data with their labels independently is much easier than addressing labeled multi-modal data. To obtain the common representations under such a situation, we propose to make the distributions over different modalities similar in the learned representations, namely modality-invariant representations. In particular, we propose a novel algorithm for modality-invariant representation learning, named Deep Modality Invariant Adversarial Network (DeMIAN), which utilizes the idea of Domain Adaptation (DA). Using the modality-invariant representations learned by DeMIAN, we achieved better classification accuracy than with the state-of-the-art methods, especially for some benchmark datasets of zero-shot learning.
Tasks	Domain Adaptation, Representation Learning, Zero-Shot Learning
Published	2016-12-23
URL	http://arxiv.org/abs/1612.07976v2
PDF	http://arxiv.org/pdf/1612.07976v2.pdf
PWC	https://paperswithcode.com/paper/demian-deep-modality-invariant-adversarial
Repo
Framework

A Joint Indoor WLAN Localization and Outlier Detection Scheme Using LASSO and Elastic-Net Optimization Techniques


Title	A Joint Indoor WLAN Localization and Outlier Detection Scheme Using LASSO and Elastic-Net Optimization Techniques
Authors	Ali Khalajmehrabadi, Nikolaos Gatsis, Daniel Pack, David Akopian
Abstract	In this paper, we introduce two indoor Wireless Local Area Network (WLAN) positioning methods using augmented sparse recovery algorithms. These schemes render a sparse user’s position vector, and in parallel, minimize the distance between the online measurement and radio map. The overall localization scheme for both methods consists of three steps: 1) coarse localization, obtained from comparing the online measurements with clustered radio map. A novel graph-based method is proposed to cluster the offline fingerprints. In the online phase, a Region Of Interest (ROI) is selected within which we search for the user’s location; 2) Access Point (AP) selection; and 3) fine localization through the novel sparse recovery algorithms. Since the online measurements are subject to inordinate measurement readings, called outliers, the sparse recovery methods are modified in order to jointly estimate the outliers and user’s position vector. The outlier detection procedure identifies the APs whose readings are either not available or erroneous. The proposed localization methods have been tested with Received Signal Strength (RSS) measurements in a typical office environment and the results show that they can localize the user with significantly high accuracy and resolution which is superior to the results from competing WLAN fingerprinting localization methods.
Tasks	Outlier Detection
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05419v1
PDF	http://arxiv.org/pdf/1610.05419v1.pdf
PWC	https://paperswithcode.com/paper/a-joint-indoor-wlan-localization-and-outlier
Repo
Framework