January 31, 2020

3392 words 16 mins read

Paper Group ANR 65

A Dynamic Sampling Adaptive-SGD Method for Machine Learning. An Innovative Approach to Addressing Childhood Obesity: A Knowledge-Based Infrastructure for Supporting Multi-Stakeholder Partnership Decision-Making in Quebec, Canada. Learning to Observe: Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations. Pa …

A Dynamic Sampling Adaptive-SGD Method for Machine Learning


Title	A Dynamic Sampling Adaptive-SGD Method for Machine Learning
Authors	Achraf Bahamou, Donald Goldfarb
Abstract	We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such directions, eliminating the need for the user to tune the learning rate. The proposed method exploits local curvature information and ensures that search directions are descent directions with high probability using an acute-angle test and can be used as a method that has a global linear rate of convergence on self-concordant functions with high probability. Numerical experiments show that this method is able to choose the best learning rates and compares favorably to fine-tuned SGD for training logistic regression and DNNs. We also propose an adaptive version of ADAM that eliminates the need to tune the base learning rate and compares favorably to fine-tuned ADAM on training DNNs. In our DNN experiments, we rarely encountered negative curvature at the current point along the step direction in DNNs.
Tasks	Stochastic Optimization
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13357v2
PDF	https://arxiv.org/pdf/1912.13357v2.pdf
PWC	https://paperswithcode.com/paper/a-dynamic-sampling-adaptive-sgd-method-for
Repo
Framework

An Innovative Approach to Addressing Childhood Obesity: A Knowledge-Based Infrastructure for Supporting Multi-Stakeholder Partnership Decision-Making in Quebec, Canada


Title	An Innovative Approach to Addressing Childhood Obesity: A Knowledge-Based Infrastructure for Supporting Multi-Stakeholder Partnership Decision-Making in Quebec, Canada
Authors	Nii Antiaye Addy, Arash Shaban-Nejad, David L. Buckeridge, Laurette Dubé
Abstract	The purpose of this paper is to describe and analyze the development of a knowledge-based infrastructure to support MSP decision-making processes. The paper emerged from a study to define specifications for a knowledge-based infrastructure to provide decision support for community-level MSPs in the Canadian province of Quebec. As part of the study, a process assessment was conducted to understand the needs of communities as they collect, organize, and analyze data to make decisions about their priorities. The result of this process is a portrait, which is an epidemiological profile of health and nutrition in their community. Portraits inform strategic planning and development of interventions and are used to assess the impact of interventions. Our key findings indicate ambiguities and disagreement among MSP decision-makers regarding causal relationships between actions and outcomes, and the relevant data needed for making decisions. MSP decision-makers expressed a desire for easy-to-use tools that facilitate the collection, organization, synthesis, and analysis of data, to enable decision-making in a timely manner. Findings inform conceptual modeling and ontological analysis to capture the domain knowledge and specify relationships between actions and outcomes. This modeling and analysis provide the foundation for an ontology, encoded using OWL 2 Web Ontology Language. The ontology is developed to provide semantic support for the MSP process, defining objectives, strategies, actions, indicators, and data sources. In the future, software interacting with the ontology can facilitate interactive browsing by decision-makers in the MSP in the form of concepts, instances, relationships, and axioms. Our ontology also facilitates the integration and interpretation of community data and can help in managing semantic interoperability between different knowledge sources.
Tasks	Decision Making
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09763v1
PDF	https://arxiv.org/pdf/1911.09763v1.pdf
PWC	https://paperswithcode.com/paper/an-innovative-approach-to-addressing
Repo
Framework

Learning to Observe: Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations


Title	Learning to Observe: Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations
Authors	Alan Dolhasz, Carlo Harvey, Ian Williams
Abstract	Many tasks in computer vision are often calibrated and evaluated relative to human perception. In this paper, we propose to directly approximate the perceptual function performed by human observers completing a visual detection task. Specifically, we present a novel methodology for learning to detect image transformations visible to human observers through approximating perceptual thresholds. To do this, we carry out a subjective two-alternative forced-choice study to estimate perceptual thresholds of human observers detecting local exposure shifts in images. We then leverage transformation equivariant representation learning to overcome issues of limited perceptual data. This representation is then used to train a dense convolutional classifier capable of detecting local suprathreshold exposure shifts - a distortion common to image composites. In this context, our model can approximate perceptual thresholds with an average error of 0.1148 exposure stops between empirical and predicted thresholds. It can also be trained to detect a range of different local transformations.
Tasks	Representation Learning
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06433v2
PDF	https://arxiv.org/pdf/1912.06433v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-observe-approximating-human
Repo
Framework

Patch Aggregator for Scene Text Script Identification


Title	Patch Aggregator for Scene Text Script Identification
Authors	Changxu Cheng, Qiuhui Huang, Xiang Bai, Bin Feng, Wenyu Liu
Abstract	Script identification in the wild is of great importance in a multi-lingual robust-reading system. The scripts deriving from the same language family share a large set of characters, which makes script identification a fine-grained classification problem. Most existing methods make efforts to learn a single representation that combines the local features by making a weighted average or other clustering methods, which may reduce the discriminatory power of some important parts in each script for the interference of redundant features. In this paper, we present a novel module named Patch Aggregator (PA), which learns a more discriminative representation for script identification by taking into account the prediction scores of local patches. Specifically, we design a CNN-based method consisting of a standard CNN classifier and a PA module. Experiments demonstrate that the proposed PA module brings significant performance improvements over the baseline CNN model, achieving the state-of-the-art results on three benchmark datasets for script identification: SIW-13, CVSI 2015 and RRC-MLT 2017.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03818v1
PDF	https://arxiv.org/pdf/1912.03818v1.pdf
PWC	https://paperswithcode.com/paper/patch-aggregator-for-scene-text-script
Repo
Framework

Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity


Title	Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity
Authors	Vladislav Golyanik, André Jonas, Didier Stricker, Christian Theobalt
Abstract	While dense non-rigid structure from motion (NRSfM) has been extensively studied from the perspective of the reconstructability problem over the recent years, almost no attempts have been undertaken to bring it into the practical realm. The reasons for the slow dissemination are the severe ill-posedness, high sensitivity to motion and deformation cues and the difficulty to obtain reliable point tracks in the vast majority of practical scenarios. To fill this gap, we propose a hybrid approach that extracts prior shape knowledge from an input sequence with NRSfM and uses it as a dynamic shape prior for sequential surface recovery in scenarios with recurrence. Our Dynamic Shape Prior Reconstruction (DSPR) method can be combined with existing dense NRSfM techniques while its energy functional is optimised with stochastic gradient descent at real-time rates for new incoming point tracks. The proposed versatile framework with a new core NRSfM approach outperforms several other methods in the ability to handle inaccurate and noisy point tracks, provided we have access to a representative (in terms of the deformation variety) image sequence. Comprehensive experiments highlight convergence properties and the accuracy of DSPR under different disturbing effects. We also perform a joint study of tracking and reconstruction and show applications to shape compression and heart reconstruction under occlusions. We achieve state-of-the-art metrics (accuracy and compression ratios) in different scenarios.
Tasks
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02468v1
PDF	https://arxiv.org/pdf/1909.02468v1.pdf
PWC	https://paperswithcode.com/paper/intrinsic-dynamic-shape-prior-for-fast
Repo
Framework

Twitter Sentiment on Affordable Care Act using Score Embedding


Title	Twitter Sentiment on Affordable Care Act using Score Embedding
Authors	Mohsen Farhadloo
Abstract	In this paper we introduce score embedding, a neural network based model to learn interpretable vector representations for words. Score embedding is a supervised method that takes advantage of the labeled training data and the neural network architecture to learn interpretable representations for words. Health care has been a controversial issue between political parties in the United States. In this paper we use the discussions on Twitter regarding different issues of affordable care act to identify the public opinion about the existing health care plans using the proposed score embedding. Our results indicate our approach effectively incorporates the sentiment information and outperforms or is at least comparable to the state-of-the-art methods and the negative sentiment towards “TrumpCare” was consistently greater than neutral and positive sentiment over time.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.07061v1
PDF	https://arxiv.org/pdf/1908.07061v1.pdf
PWC	https://paperswithcode.com/paper/twitter-sentiment-on-affordable-care-act
Repo
Framework

ADASS: Adaptive Sample Selection for Training Acceleration


Title	ADASS: Adaptive Sample Selection for Training Acceleration
Authors	Shen-Yi Zhao, Hao Gao, Wu-Jun Li
Abstract	Stochastic gradient decent~(SGD) and its variants, including some accelerated variants, have become popular for training in machine learning. However, in all existing SGD and its variants, the sample size in each iteration~(epoch) of training is the same as the size of the full training set. In this paper, we propose a new method, called \underline{ada}ptive \underline{s}ample \underline{s}election~(ADASS), for training acceleration. During different epoches of training, ADASS only need to visit different training subsets which are adaptively selected from the full training set according to the Lipschitz constants of the loss functions on samples. It means that in ADASS the sample size in each epoch of training can be smaller than the size of the full training set, by discarding some samples. ADASS can be seamlessly integrated with existing optimization methods, such as SGD and momentum SGD, for training acceleration. Theoretical results show that the learning accuracy of ADASS is comparable to that of counterparts with full training set. Furthermore, empirical results on both shallow models and deep models also show that ADASS can accelerate the training process of existing methods without sacrificing accuracy.
Tasks
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04819v2
PDF	https://arxiv.org/pdf/1906.04819v2.pdf
PWC	https://paperswithcode.com/paper/adass-adaptive-sample-selection-for-training
Repo
Framework

Bridging the Gap Between Computational Photography and Visual Recognition


Title	Bridging the Gap Between Computational Photography and Visual Recognition
Authors	Rosaura G. VidalMata, Sreya Banerjee, Brandon RichardWebster, Michael Albright, Pedro Davalos, Scott McCloskey, Ben Miller, Asong Tambo, Sushobhan Ghosh, Sudarshan Nagesh, Ye Yuan, Yueyu Hu, Junru Wu, Wenhan Yang, Xiaoshuai Zhang, Jiaying Liu, Zhangyang Wang, Hwann-Tzong Chen, Tzu-Wei Huang, Wen-Chi Chin, Yi-Chun Li, Mahmoud Lababidi, Charles Otto, Walter J. Scheirer
Abstract	What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step to improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressing need for the development of algorithms that are designed for the joint problem of improving visual appearance and recognition, which will be an enabling factor for the deployment of visual recognition tools in many real-world scenarios. To address this, we introduce the UG^2 dataset as a large-scale benchmark composed of video imagery captured under challenging conditions, and two enhancement tasks designed to test algorithmic impact on visual quality and automatic object recognition. Furthermore, we propose a set of metrics to evaluate the joint improvement of such tasks as well as individual algorithmic advances, including a novel psychophysics-based evaluation regime for human assessment and a realistic set of quantitative measures for object recognition performance. We introduce six new algorithms for image restoration or enhancement, which were created as part of the IARPA sponsored UG^2 Challenge workshop held at CVPR 2018. Under the proposed evaluation regime, we present an in-depth analysis of these algorithms and a host of deep learning-based and classic baseline approaches. From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.
Tasks	Image Restoration, Object Recognition
Published	2019-01-28
URL	https://arxiv.org/abs/1901.09482v3
PDF	https://arxiv.org/pdf/1901.09482v3.pdf
PWC	https://paperswithcode.com/paper/bridging-the-gap-between-computational
Repo
Framework

Terminologies augmented recurrent neural network model for clinical named entity recognition


Title	Terminologies augmented recurrent neural network model for clinical named entity recognition
Authors	Ivan Lerner, Nicolas Paris, Xavier Tannier
Abstract	We aimed to enhance the performance of a supervised model for clinical named-entity recognition (NER) using medical terminologies. In order to evaluate our system in French, we built a corpus for 5 types of clinical entities. We used a terminology-based system as baseline, built upon UMLS and SNOMED. Then, we evaluated a biGRU-CRF, and an hybrid system using the prediction of the terminology-based system as feature for the biGRU-CRF. In English, we evaluated the NER systems on the i2b2-2009 Medication Challenge for Drug name recognition, which contained 8,573 entities for 268 documents. In French, we built APcNER, a corpus of 147 documents annotated for 5 entities (drug name, sign or symptom, disease or disorder, diagnostic procedure or lab test and therapeutic procedure). We evaluated each NER systems using exact and partial match definition of F-measure for NER. The APcNER contains 4,837 entities which took 28 hours to annotate, the inter-annotator agreement was acceptable for Drug name in exact match (85%) and acceptable for other entity types in non-exact match (>70%). For drug name recognition on both i2b2-2009 and APcNER, the biGRU-CRF performed better that the terminology-based system, with an exact-match F-measure of 91.1% versus 73% and 81.9% versus 75% respectively. Moreover, the hybrid system outperformed the biGRU-CRF, with an exact-match F-measure of 92.2% versus 91.1% (i2b2-2009) and 88.4% versus 81.9% (APcNER). On APcNER corpus, the micro-average F-measure of the hybrid system on the 5 entities was 69.5% in exact match, and 84.1% in non-exact match. APcNER is a French corpus for clinical-NER of five type of entities which covers a large variety of document types. Extending supervised model with terminology allowed for an easy performance gain, especially in low regimes of entities, and established near state of the art results on the i2b2-2009 corpus.
Tasks	Named Entity Recognition
Published	2019-04-25
URL	https://arxiv.org/abs/1904.11473v2
PDF	https://arxiv.org/pdf/1904.11473v2.pdf
PWC	https://paperswithcode.com/paper/terminologies-augmented-recurrent-neural
Repo
Framework

Learn and Link: Learning Critical Regions for Efficient Planning


Title	Learn and Link: Learning Critical Regions for Efficient Planning
Authors	Daniel Molina, Kislay Kumar, Siddharth Srivastava
Abstract	This paper presents a new approach to learning for motion planning (MP) where critical regions of an environment are learned from a given set of motion plans and used to improve performance on new environments and problem instances. We introduce a new suite of sampling-based motion planners, Learn and Link. Our planners leverage critical regions to overcome the limitations of uniform sampling, while still maintaining guarantees of correctness inherent to sampling-based algorithms. We also show that convolutional neural networks (CNNs) can be used to identify critical regions for motion planning problems. We evaluate Learn and Link against planners from the Open Motion Planning Library (OMPL) using an extensive suite of experiments on challenging motion planning problems. We show that our approach requires far less planning time than existing sampling-based planners.
Tasks	Motion Planning
Published	2019-03-08
URL	https://arxiv.org/abs/1903.03258v4
PDF	https://arxiv.org/pdf/1903.03258v4.pdf
PWC	https://paperswithcode.com/paper/identifying-critical-regions-for-motion
Repo
Framework

The meta-problem and the transfer of knowledge between theories of consciousness: a software engineer’s take


Title	The meta-problem and the transfer of knowledge between theories of consciousness: a software engineer’s take
Authors	Marcel Kvassay
Abstract	This contribution examines two radically different explanations of our phenomenal intuitions, one reductive and one strongly non-reductive, and identifies two germane ideas that could benefit many other theories of consciousness. Firstly, the ability of sophisticated agent architectures with a purely physical implementation to support certain functional forms of qualia or proto-qualia appears to entail the possibility of machine consciousness with qualia, not only for reductive theories but also for the nonreductive ones that regard consciousness as ubiquitous in Nature. Secondly, analysis of introspective psychological material seems to hint that, under the threshold of our ordinary waking awareness, there exist further ‘submerged’ or ‘subliminal’ layers of consciousness which constitute a hidden foundation and support and another source of our phenomenal intuitions. These ‘submerged’ layers might help explain certain puzzling phenomena concerning subliminal perception, such as the apparently ‘unconscious’ multisensory integration and learning of subliminal stimuli.
Tasks
Published	2019-02-18
URL	http://arxiv.org/abs/1903.03418v1
PDF	http://arxiv.org/pdf/1903.03418v1.pdf
PWC	https://paperswithcode.com/paper/the-meta-problem-and-the-transfer-of
Repo
Framework

Improving Joint Training of Inference Networks and Structured Prediction Energy Networks


Title	Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Authors	Lifu Tu, Richard Yuanzhe Pang, Kevin Gimpel
Abstract	Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energy-based models by training “inference networks” to approximate structured inference instead of using gradient descent. However, their alternating optimization approach suffers from instabilities during training, requiring additional loss terms and careful hyperparameter tuning. In this paper, we contribute several strategies to stabilize and improve this joint training of energy functions and inference networks for structured prediction. We design a compound objective to jointly train both cost-augmented and test-time inference networks along with the energy function. We propose joint parameterizations for the inference networks that encourage them to capture complementary functionality during learning. We empirically validate our strategies on two sequence labeling tasks, showing easier paths to strong performance than prior work, as well as further improvements with global energy terms.
Tasks	Structured Prediction
Published	2019-11-07
URL	https://arxiv.org/abs/1911.02891v1
PDF	https://arxiv.org/pdf/1911.02891v1.pdf
PWC	https://paperswithcode.com/paper/improving-joint-training-of-inference
Repo
Framework

Group Representation Theory for Knowledge Graph Embedding


Title	Group Representation Theory for Knowledge Graph Embedding
Authors	Chen Cai
Abstract	Knowledge graph embedding has recently become a popular way to model relations and infer missing links. In this paper, we present a group theoretical perspective of knowledge graph embedding, connecting previous methods with different group actions. Furthermore, by utilizing Schur’s lemma from group representation theory, we show that the state of the art embedding method RotatE can model relations from any finite Abelian group.
Tasks	Graph Embedding, Knowledge Graph Embedding
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05100v2
PDF	https://arxiv.org/pdf/1909.05100v2.pdf
PWC	https://paperswithcode.com/paper/group-representation-theory-for-knowledge
Repo
Framework

CNN-Based Invertible Wavelet Scattering for the Investigation of Diffusion Properties of the In Vivo Human Heart in Diffusion Tensor Imaging


Title	CNN-Based Invertible Wavelet Scattering for the Investigation of Diffusion Properties of the In Vivo Human Heart in Diffusion Tensor Imaging
Authors	Zeyu Deng, Lihui Wang, Zixiang Kuai, Qijian Chen, Xinyu Cheng, Feng Yang, Jie Yang, Yuemin Zhu
Abstract	In vivo diffusion tensor imaging (DTI) is a promising technique to investigate noninvasively the fiber structures of the in vivo human heart. However, signal loss due to motions remains a persistent problem in in vivo cardiac DTI. We propose a novel motion-compensation method for investigating in vivo myocardium structures in DTI with free-breathing acquisitions. The method is based on an invertible Wavelet Scattering achieved by means of Convolutional Neural Network (WSCNN). It consists of first extracting translation-invariant wavelet scattering features from DW images acquired at different trigger delays and then mapping the fused scattering features into motion-compensated spatial DW images by performing an inverse wavelet scattering transform achieved using CNN. The results on both simulated and acquired in vivo cardiac DW images showed that the proposed WSCNN method effectively compensates for motion-induced signal loss and produces in vivo cardiac DW images with better quality and more coherent fiber structures with respect to existing methods, which makes it an interesting method for measuring correctly the diffusion properties of the in vivo human heart in DTI under free breathing.
Tasks	Motion Compensation
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07776v1
PDF	https://arxiv.org/pdf/1912.07776v1.pdf
PWC	https://paperswithcode.com/paper/cnn-based-invertible-wavelet-scattering-for
Repo
Framework

Phoneme-Based Persian Speech Recognition


Title	Phoneme-Based Persian Speech Recognition
Authors	Saber Malekzadeh
Abstract	Undoubtedly, one of the most important issues in computer science is intelligent speech recognition. In these systems, computers try to detect and respond to the speeches they are listening to, like humans. In this research, presenting of a suitable method for the diagnosis of Persian phonemes by AI using the signal processing and classification algorithms have tried. For this purpose, the STFT algorithm has been used to process the audio signals, as well as to detect and classify the signals processed by the deep artificial neural network. At first, educational samples were provided as two phonological phrases in Persian language and then signal processing operations were performed on them. Then the results for the data training have been given to the artificial deep neural network. At the final stage, the experiment was conducted on new sounds.
Tasks	Speech Recognition
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04699v1
PDF	http://arxiv.org/pdf/1901.04699v1.pdf
PWC	https://paperswithcode.com/paper/phoneme-based-persian-speech-recognition
Repo
Framework