October 18, 2019

3258 words 16 mins read

Paper Group ANR 653

Simultaneous 12-Lead Electrocardiogram Synthesis using a Single-Lead ECG Signal: Application to Handheld ECG Devices. Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses. Cross-Lingual Task-Specific Representation Learning for Text Classification in Resource Poor Languages. A Saliency-based Convolutional Neural Netwo …

Simultaneous 12-Lead Electrocardiogram Synthesis using a Single-Lead ECG Signal: Application to Handheld ECG Devices


Title	Simultaneous 12-Lead Electrocardiogram Synthesis using a Single-Lead ECG Signal: Application to Handheld ECG Devices
Authors	Kahkashan Afrin, Parikshit Verma, Sanjay S. Srivatsa, Satish T. S. Bukkapatnam
Abstract	Recent introduction of wearable single-lead ECG devices of diverse configurations has caught the intrigue of the medical community. While these devices provide a highly affordable support tool for the caregivers for continuous monitoring and to detect acute conditions, such as arrhythmia, their utility for cardiac diagnostics remains limited. This is because clinical diagnosis of many cardiac pathologies is rooted in gleaning patterns from synchronous 12-lead ECG. If synchronous 12-lead signals of clinical quality can be synthesized from these single-lead devices, it can transform cardiac care by substantially reducing the costs and enhancing access to cardiac diagnostics. However, prior attempts to synthesize synchronous 12-lead ECG have not been successful. Vectorcardiography (VCG) analysis suggests that cardiac axis synthesized from earlier attempts deviates significantly from that estimated from 12-lead and/or Frank lead measurements. This work is perhaps the first successful attempt to synthesize clinically equivalent synchronous 12-lead ECG from single-lead ECG. Our method employs a random forest machine learning model that uses a subject’s historical 12-lead recordings to estimate the morphology including the actual timing of various ECG events (relative to the measured single-lead ECG) for all 11 missing leads of the subject. Our method was validated on two benchmark datasets as well as paper ECG and AliveCor-Kardia data obtained from the Heart, Artery, and Vein Center of Fresno, California. Results suggest that this approach can synthesize synchronous ECG with accuracies (R2) exceeding 90%. Accurate synthesis of 12-lead ECG from a single-lead device can ultimately enable its wider application and improved point-of-care (POC) diagnostics.
Tasks
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08035v1
PDF	http://arxiv.org/pdf/1811.08035v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-12-lead-electrocardiogram
Repo
Framework

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses


Title	Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses
Authors	Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann
Abstract	Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system. Incorporating this in deep learning frameworks would allow us to explicitly encode known notions of geometry, instead of having the network implicitly learn them from data. However, performing eigendecomposition within a network requires the ability to differentiate this operation. Unfortunately, while theoretically doable, this introduces numerical instability in the optimization process in practice. In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network. We demonstrate on several tasks, including keypoint matching and 3D pose estimation, that our approach is much more robust than explicit differentiation of the eigendecomposition, It has better convergence properties and yields state-of-the-art results on both tasks.
Tasks	3D Pose Estimation, Pose Estimation
Published	2018-03-21
URL	http://arxiv.org/abs/1803.08071v2
PDF	http://arxiv.org/pdf/1803.08071v2.pdf
PWC	https://paperswithcode.com/paper/eigendecomposition-free-training-of-deep
Repo
Framework

Cross-Lingual Task-Specific Representation Learning for Text Classification in Resource Poor Languages


Title	Cross-Lingual Task-Specific Representation Learning for Text Classification in Resource Poor Languages
Authors	Nurendra Choudhary, Rajat Singh, Manish Shrivastava
Abstract	Neural network models have shown promising results for text classification. However, these solutions are limited by their dependence on the availability of annotated data. The prospect of leveraging resource-rich languages to enhance the text classification of resource-poor languages is fascinating. The performance on resource-poor languages can significantly improve if the resource availability constraints can be offset. To this end, we present a twin Bidirectional Long Short Term Memory (Bi-LSTM) network with shared parameters consolidated by a contrastive loss function (based on a similarity metric). The model learns the representation of resource-poor and resource-rich sentences in a common space by using the similarity between their assigned annotation tags. Hence, the model projects sentences with similar tags closer and those with different tags farther from each other. We evaluated our model on the classification tasks of sentiment analysis and emoji prediction for resource-poor languages - Hindi and Telugu and resource-rich languages - English and Spanish. Our model significantly outperforms the state-of-the-art approaches in both the tasks across all metrics.
Tasks	Representation Learning, Sentiment Analysis, Text Classification
Published	2018-06-10
URL	http://arxiv.org/abs/1806.03590v1
PDF	http://arxiv.org/pdf/1806.03590v1.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-task-specific-representation
Repo
Framework

A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized Documents


Title	A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized Documents
Authors	I. Kavasidis, S. Palazzo, C. Spampinato, C. Pino, D. Giordano, D. Giuffrida, P. Messina
Abstract	Deep Convolutional Neural Networks (DCNNs) have recently been applied successfully to a variety of vision and multimedia tasks, thus driving development of novel solutions in several application domains. Document analysis is a particularly promising area for DCNNs: indeed, the number of available digital documents has reached unprecedented levels, and humans are no longer able to discover and retrieve all the information contained in these documents without the help of automation. Under this scenario, DCNNs offers a viable solution to automate the information extraction process from digital documents. Within the realm of information extraction from documents, detection of tables and charts is particularly needed as they contain a visual summary of the most valuable information contained in a document. For a complete automation of visual information extraction process from tables and charts, it is necessary to develop techniques that localize them and identify precisely their boundaries. In this paper we aim at solving the table/chart detection task through an approach that combines deep convolutional neural networks, graphical models and saliency concepts. In particular, we propose a saliency-based fully-convolutional neural network performing multi-scale reasoning on visual cues followed by a fully-connected conditional random field (CRF) for localizing tables and charts in digital/digitized documents. Performance analysis carried out on an extended version of ICDAR 2013 (with annotated charts as well as tables) shows that our approach yields promising results, outperforming existing models.
Tasks
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06236v1
PDF	http://arxiv.org/pdf/1804.06236v1.pdf
PWC	https://paperswithcode.com/paper/a-saliency-based-convolutional-neural-network
Repo
Framework

Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration


Title	Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration
Authors	Seyed Sadegh Mohseni Salehi, Shadab Khan, Deniz Erdogmus, Ali Gholipour
Abstract	With an aim to increase the capture range and accelerate the performance of state-of-the-art inter-subject and subject-to-template 3D registration, we propose deep learning-based methods that are trained to find the 3D position of arbitrarily oriented subjects or anatomy based on slices or volumes of medical images. For this, we propose regression CNNs that learn to predict the angle-axis representation of 3D rotations and translations using image features. We use and compare mean square error and geodesic loss to train regression CNNs for 3D pose estimation used in two different scenarios: slice-to-volume registration and volume-to-volume registration. Our results show that in such registration applications that are amendable to learning, the proposed deep learning methods with geodesic loss minimization can achieve accurate results with a wide capture range in real-time (<100ms). We also tested the generalization capability of the trained CNNs on an expanded age range and on images of newborn subjects with similar and different MR image contrasts. We trained our models on T2-weighted fetal brain MRI scans and used them to predict the 3D pose of newborn brains based on T1-weighted MRI scans. We showed that the trained models generalized well for the new domain when we performed image contrast transfer through a conditional generative adversarial network. This indicates that the domain of application of the trained deep regression CNNs can be further expanded to image modalities and contrasts other than those used in training. A combination of our proposed methods with accelerated optimization-based registration algorithms can dramatically enhance the performance of automatic imaging devices and image processing methods of the future.
Tasks	3D Pose Estimation, Pose Estimation
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05982v4
PDF	http://arxiv.org/pdf/1803.05982v4.pdf
PWC	https://paperswithcode.com/paper/real-time-deep-pose-estimation-with-geodesic
Repo
Framework

Lost in Translation: Analysis of Information Loss During Machine Translation Between Polysynthetic and Fusional Languages


Title	Lost in Translation: Analysis of Information Loss During Machine Translation Between Polysynthetic and Fusional Languages
Authors	Manuel Mager, Elisabeth Mager, Alfonso Medina-Urrea, Ivan Meza, Katharina Kann
Abstract	Machine translation from polysynthetic to fusional languages is a challenging task, which gets further complicated by the limited amount of parallel text available. Thus, translation performance is far from the state of the art for high-resource and more intensively studied language pairs. To shed light on the phenomena which hamper automatic translation to and from polysynthetic languages, we study translations from three low-resource, polysynthetic languages (Nahuatl, Wixarika and Yorem Nokki) into Spanish and vice versa. Doing so, we find that in a morpheme-to-morpheme alignment an important amount of information contained in polysynthetic morphemes has no Spanish counterpart, and its translation is often omitted. We further conduct a qualitative analysis and, thus, identify morpheme types that are commonly hard to align or ignored in the translation process.
Tasks	Machine Translation
Published	2018-07-01
URL	http://arxiv.org/abs/1807.00286v1
PDF	http://arxiv.org/pdf/1807.00286v1.pdf
PWC	https://paperswithcode.com/paper/lost-in-translation-analysis-of-information
Repo
Framework

Machine Learning in High Energy Physics Community White Paper


Title	Machine Learning in High Energy Physics Community White Paper
Authors	Kim Albertsson, Piero Altoe, Dustin Anderson, John Anderson, Michael Andrews, Juan Pedro Araque Espinosa, Adam Aurisano, Laurent Basara, Adrian Bevan, Wahid Bhimji, Daniele Bonacorsi, Bjorn Burkle, Paolo Calafiura, Mario Campanelli, Louis Capps, Federico Carminati, Stefano Carrazza, Yi-fan Chen, Taylor Childers, Yann Coadou, Elias Coniavitis, Kyle Cranmer, Claire David, Douglas Davis, Andrea De Simone, Javier Duarte, Martin Erdmann, Jonas Eschle, Amir Farbin, Matthew Feickert, Nuno Filipe Castro, Conor Fitzpatrick, Michele Floris, Alessandra Forti, Jordi Garra-Tico, Jochen Gemmler, Maria Girone, Paul Glaysher, Sergei Gleyzer, Vladimir Gligorov, Tobias Golling, Jonas Graw, Lindsey Gray, Dick Greenwood, Thomas Hacker, John Harvey, Benedikt Hegner, Lukas Heinrich, Ulrich Heintz, Ben Hooberman, Johannes Junggeburth, Michael Kagan, Meghan Kane, Konstantin Kanishchev, Przemysław Karpiński, Zahari Kassabov, Gaurav Kaul, Dorian Kcira, Thomas Keck, Alexei Klimentov, Jim Kowalkowski, Luke Kreczko, Alexander Kurepin, Rob Kutschke, Valentin Kuznetsov, Nicolas Köhler, Igor Lakomov, Kevin Lannon, Mario Lassnig, Antonio Limosani, Gilles Louppe, Aashrita Mangu, Pere Mato, Narain Meenakshi, Helge Meinhard, Dario Menasce, Lorenzo Moneta, Seth Moortgat, Mark Neubauer, Harvey Newman, Sydney Otten, Hans Pabst, Michela Paganini, Manfred Paulini, Gabriel Perdue, Uzziel Perez, Attilio Picazio, Jim Pivarski, Harrison Prosper, Fernanda Psihas, Alexander Radovic, Ryan Reece, Aurelius Rinkevicius, Eduardo Rodrigues, Jamal Rorie, David Rousseau, Aaron Sauers, Steven Schramm, Ariel Schwartzman, Horst Severini, Paul Seyfert, Filip Siroky, Konstantin Skazytkin, Mike Sokoloff, Graeme Stewart, Bob Stienen, Ian Stockdale, Giles Strong, Wei Sun, Savannah Thais, Karen Tomko, Eli Upfal, Emanuele Usai, Andrey Ustyuzhanin, Martin Vala, Justin Vasel, Sofia Vallecorsa, Mauro Verzetti, Xavier Vilasís-Cardona, Jean-Roch Vlimant, Ilija Vukotic, Sean-Jiun Wang, Gordon Watts, Michael Williams, Wenjing Wu, Stefan Wunsch, Kun Yang, Omar Zapata
Abstract	Machine learning has been applied to several problems in particle physics research, beginning with applications to high-level physics analysis in the 1990s and 2000s, followed by an explosion of applications in particle and event identification and reconstruction in the 2010s. In this document we discuss promising future research and development areas for machine learning in particle physics. We detail a roadmap for their implementation, software and hardware resource requirements, collaborative initiatives with the data science community, academia and industry, and training the particle physics community in data science. The main objective of the document is to connect and motivate these areas of research and development with the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments and identify the resource needs for their implementation. Additionally we identify areas where collaboration with external communities will be of great benefit.
Tasks
Published	2018-07-08
URL	https://arxiv.org/abs/1807.02876v3
PDF	https://arxiv.org/pdf/1807.02876v3.pdf
PWC	https://paperswithcode.com/paper/machine-learning-in-high-energy-physics
Repo
Framework

Gaussian Processes indexed on the symmetric group: prediction and learning


Title	Gaussian Processes indexed on the symmetric group: prediction and learning
Authors	François Bachoc, Baptiste Broto, Fabrice Gamboa, Jean-Michel Loubes
Abstract	In the framework of the supervised learning of a real function defined on a space X , the so called Kriging method stands on a real Gaussian field defined on X. The Euclidean case is well known and has been widely studied. In this paper, we explore the less classical case where X is the non commutative finite group of permutations. In this setting, we propose and study an harmonic analysis of the covariance operators that enables to consider Gaussian processes models and forecasting issues. Our theory is motivated by statistical ranking problems.
Tasks	Gaussian Processes
Published	2018-03-16
URL	https://arxiv.org/abs/1803.06118v4
PDF	https://arxiv.org/pdf/1803.06118v4.pdf
PWC	https://paperswithcode.com/paper/gaussian-processes-indexed-on-the-symmetric
Repo
Framework

A Mathematical Framework for Deep Learning in Elastic Source Imaging


Title	A Mathematical Framework for Deep Learning in Elastic Source Imaging
Authors	Jaejun Yoo, Abdul Wahab, Jong Chul Ye
Abstract	An inverse elastic source problem with sparse measurements is of concern. A generic mathematical framework is proposed which incorporates a low- dimensional manifold regularization in the conventional source reconstruction algorithms thereby enhancing their performance with sparse datasets. It is rigorously established that the proposed framework is equivalent to the so-called \emph{deep convolutional framelet expansion} in machine learning literature for inverse problems. Apposite numerical examples are furnished to substantiate the efficacy of the proposed framework.
Tasks
Published	2018-02-27
URL	http://arxiv.org/abs/1802.10055v3
PDF	http://arxiv.org/pdf/1802.10055v3.pdf
PWC	https://paperswithcode.com/paper/a-mathematical-framework-for-deep-learning-in
Repo
Framework

A Survey on Deep Transfer Learning


Title	A Survey on Deep Transfer Learning
Authors	Chuanqi Tan, Fuchun Sun, Tao Kong, Wenchang Zhang, Chao Yang, Chunfang Liu
Abstract	As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation, which limits its development. Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates us to use transfer learning to solve the problem of insufficient training data. This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications. We defined deep transfer learning, category and review the recent research works based on the techniques used in deep transfer learning.
Tasks	Transfer Learning
Published	2018-08-06
URL	http://arxiv.org/abs/1808.01974v1
PDF	http://arxiv.org/pdf/1808.01974v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-deep-transfer-learning
Repo
Framework

D2KE: From Distance to Kernel and Embedding


Title	D2KE: From Distance to Kernel and Embedding
Authors	Lingfei Wu, Ian En-Hsu Yen, Fangli Xu, Pradeep Ravikumar, Michael Witbrock
Abstract	For many machine learning problem settings, particularly with structured inputs such as sequences or sets of objects, a distance measure between inputs can be specified more naturally than a feature representation. However, most standard machine models are designed for inputs with a vector feature representation. In this work, we consider the estimation of a function $f:\mathcal{X} \rightarrow \R$ based solely on a dissimilarity measure $d:\mathcal{X}\times\mathcal{X} \rightarrow \R$ between inputs. In particular, we propose a general framework to derive a family of \emph{positive definite kernels} from a given dissimilarity measure, which subsumes the widely-used \emph{representative-set method} as a special case, and relates to the well-known \emph{distance substitution kernel} in a limiting case. We show that functions in the corresponding Reproducing Kernel Hilbert Space (RKHS) are Lipschitz-continuous w.r.t. the given distance metric. We provide a tractable algorithm to estimate a function from this RKHS, and show that it enjoys better generalizability than Nearest-Neighbor estimates. Our approach draws from the literature of Random Features, but instead of deriving feature maps from an existing kernel, we construct novel kernels from a random feature map, that we specify given the distance measure. We conduct classification experiments with such disparate domains as strings, time series, and sets of vectors, where our proposed framework compares favorably to existing distance-based learning methods such as $k$-nearest-neighbors, distance-substitution kernels, pseudo-Euclidean embedding, and the representative-set method.
Tasks	Time Series
Published	2018-02-14
URL	http://arxiv.org/abs/1802.04956v4
PDF	http://arxiv.org/pdf/1802.04956v4.pdf
PWC	https://paperswithcode.com/paper/d2ke-from-distance-to-kernel-and-embedding
Repo
Framework

Pooling of Causal Models under Counterfactual Fairness via Causal Judgement Aggregation


Title	Pooling of Causal Models under Counterfactual Fairness via Causal Judgement Aggregation
Authors	Fabio Massimo Zennaro, Magdalena Ivanovska
Abstract	In this paper we consider the problem of combining multiple probabilistic causal models, provided by different experts, under the requirement that the aggregated model satisfy the criterion of counterfactual fairness. We build upon the work on causal models and fairness in machine learning, and we express the problem of combining multiple models within the framework of opinion pooling. We propose two simple algorithms, grounded in the theory of counterfactual fairness and causal judgment aggregation, that are guaranteed to generate aggregated probabilistic causal models respecting the criterion of fairness, and we compare their behaviors on a toy case study.
Tasks
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09866v2
PDF	http://arxiv.org/pdf/1805.09866v2.pdf
PWC	https://paperswithcode.com/paper/pooling-of-causal-models-under-counterfactual
Repo
Framework

Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT


Title	Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT
Authors	Marianna J. Martindale, Marine Carpuat
Abstract	Although measuring intrinsic quality has been a key factor in the advancement of Machine Translation (MT), successfully deploying MT requires considering not just intrinsic quality but also the user experience, including aspects such as trust. This work introduces a method of studying how users modulate their trust in an MT system after seeing errorful (disfluent or inadequate) output amidst good (fluent and adequate) output. We conduct a survey to determine how users respond to good translations compared to translations that are either adequate but not fluent, or fluent but not adequate. In this pilot study, users responded strongly to disfluent translations, but were, surprisingly, much less concerned with adequacy.
Tasks	Machine Translation
Published	2018-02-16
URL	http://arxiv.org/abs/1802.06041v1
PDF	http://arxiv.org/pdf/1802.06041v1.pdf
PWC	https://paperswithcode.com/paper/fluency-over-adequacy-a-pilot-study-in
Repo
Framework

Structured Memory based Deep Model to Detect as well as Characterize Novel Inputs


Title	Structured Memory based Deep Model to Detect as well as Characterize Novel Inputs
Authors	Pratik Prabhanjan Brahma, Qiuyuan Huang, Dapeng Wu
Abstract	While deep learning has pushed the boundaries in various machine learning tasks, the current models are still far away from replicating many functions that a normal human brain can do. Explicit memorization based deep architecture have been recently proposed with the objective to understand and predict better. In this work, we design a system that involves a primary learner and an adjacent representational memory bank which is organized using a comparative learner. This spatially forked deep architecture with a structured memory can simultaneously predict and reason about the nature of an input, which may even belong to a category never seen in the training data, by relating it with the memorized past representations at the higher layers. Characterizing images of unseen object classes in both synthetic and real world datasets is used as an example to showcase the operational success of the proposed framework.
Tasks
Published	2018-01-30
URL	http://arxiv.org/abs/1801.09859v1
PDF	http://arxiv.org/pdf/1801.09859v1.pdf
PWC	https://paperswithcode.com/paper/structured-memory-based-deep-model-to-detect
Repo
Framework

Automatic Language Identification System for Hindi and Magahi


Title	Automatic Language Identification System for Hindi and Magahi
Authors	Priya Rani, Atul Kr. Ojha, Girish Nath Jha
Abstract	Language identification has become a prerequisite for all kinds of automated text processing systems. In this paper, we present a rule-based language identifier tool for two closely related Indo-Aryan languages: Hindi and Magahi. This system has currently achieved an accuracy of approx 86.34%. We hope to improve this in the future. Automatic identification of languages will be significant in the accuracy of output of Web Crawlers.
Tasks	Language Identification
Published	2018-04-13
URL	http://arxiv.org/abs/1804.05095v1
PDF	http://arxiv.org/pdf/1804.05095v1.pdf
PWC	https://paperswithcode.com/paper/automatic-language-identification-system-for
Repo
Framework