July 28, 2019

3662 words 18 mins read

Paper Group ANR 432

Preconditioned Spectral Clustering for Stochastic Block Partition Streaming Graph Challenge. Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO. Non-Stationary Bandits with Habituation and Recovery Dynamics. New Reinforcement Learning Using a Chaotic Neural Network for Emergence of “Thinking” - “Exploration” …

Preconditioned Spectral Clustering for Stochastic Block Partition Streaming Graph Challenge


Title	Preconditioned Spectral Clustering for Stochastic Block Partition Streaming Graph Challenge
Authors	David Zhuzhunashvili, Andrew Knyazev
Abstract	Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) is demonstrated to efficiently solve eigenvalue problems for graph Laplacians that appear in spectral clustering. For static graph partitioning, 10-20 iterations of LOBPCG without preconditioning result in ~10x error reduction, enough to achieve 100% correctness for all Challenge datasets with known truth partitions, e.g., for graphs with 5K/.1M (50K/1M) Vertices/Edges in 2 (7) seconds, compared to over 5,000 (30,000) seconds needed by the baseline Python code. Our Python code 100% correctly determines 98 (160) clusters from the Challenge static graphs with 0.5M (2M) vertices in 270 (1,700) seconds using 10GB (50GB) of memory. Our single-precision MATLAB code calculates the same clusters at half time and memory. For streaming graph partitioning, LOBPCG is initiated with approximate eigenvectors of the graph Laplacian already computed for the previous graph, in many cases reducing 2-3 times the number of required LOBPCG iterations, compared to the static case. Our spectral clustering is generic, i.e. assuming nothing specific of the block model or streaming, used to generate the graphs for the Challenge, in contrast to the base code. Nevertheless, in 10-stage streaming comparison with the base code for the 5K graph, the quality of our clusters is similar or better starting at stage 4 (7) for emerging edging (snowballing) streaming, while the computations are over 100-1000 faster.
Tasks	graph partitioning
Published	2017-08-21
URL	http://arxiv.org/abs/1708.07481v1
PDF	http://arxiv.org/pdf/1708.07481v1.pdf
PWC	https://paperswithcode.com/paper/preconditioned-spectral-clustering-for
Repo
Framework

Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO


Title	Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
Authors	Daniel George, Hongyu Shen, E. A. Huerta
Abstract	The exquisite sensitivity of the advanced LIGO detectors has enabled the detection of multiple gravitational wave signals. The sophisticated design of these detectors mitigates the effect of most types of noise. However, advanced LIGO data streams are contaminated by numerous artifacts known as glitches: non-Gaussian noise transients with complex morphologies. Given their high rate of occurrence, glitches can lead to false coincident detections, obscure and even mimic gravitational wave signals. Therefore, successfully characterizing and removing glitches from advanced LIGO data is of utmost importance. Here, we present the first application of Deep Transfer Learning for glitch classification, showing that knowledge from deep learning algorithms trained for real-world object recognition can be transferred for classifying glitches in time-series based on their spectrogram images. Using the Gravity Spy dataset, containing hand-labeled, multi-duration spectrograms obtained from real LIGO data, we demonstrate that this method enables optimal use of very deep convolutional neural networks for classification given small training datasets, significantly reduces the time for training the networks, and achieves state-of-the-art accuracy above 98.8%, with perfect precision-recall on 8 out of 22 classes. Furthermore, new types of glitches can be classified accurately given few labeled examples with this technique. Once trained via transfer learning, we show that the convolutional neural networks can be truncated and used as excellent feature extractors for unsupervised clustering methods to identify new classes based on their morphology, without any labeled examples. Therefore, this provides a new framework for dynamic glitch classification for gravitational wave detectors, which are expected to encounter new types of noise as they undergo gradual improvements to attain design sensitivity.
Tasks	Object Recognition, Time Series, Transfer Learning
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07446v1
PDF	http://arxiv.org/pdf/1706.07446v1.pdf
PWC	https://paperswithcode.com/paper/deep-transfer-learning-a-new-deep-learning
Repo
Framework

Non-Stationary Bandits with Habituation and Recovery Dynamics


Title	Non-Stationary Bandits with Habituation and Recovery Dynamics
Authors	Yonatan Mintz, Anil Aswani, Philip Kaminsky, Elena Flowers, Yoshimi Fukuoka
Abstract	Many settings involve sequential decision-making where a set of actions can be chosen at each time step, each action provides a stochastic reward, and the distribution for the reward of each action is initially unknown. However, frequent selection of a specific action may reduce its expected reward, while abstaining from choosing an action may cause its expected reward to increase. Such non-stationary phenomena are observed in many real world settings such as personalized healthcare-adherence improving interventions and targeted online advertising. Though finding an optimal policy for general models with non-stationarity is PSPACE-complete, we propose and analyze a new class of models called ROGUE (Reducing or Gaining Unknown Efficacy) bandits, which we show in this paper can capture these phenomena and are amenable to the design of effective policies. We first present a consistent maximum likelihood estimator for the parameters of these models. Next, we construct finite sample concentration bounds that lead to an upper confidence bound policy called the ROGUE Upper Confidence Bound (ROGUE-UCB) algorithm. We prove that under proper conditions the ROGUE-UCB algorithm achieves logarithmic in time regret, unlike existing algorithms which result in linear regret. We conclude with a numerical experiment using real data from a personalized healthcare-adherence improving intervention to increase physical activity. In this intervention, the goal is to optimize the selection of messages (e.g., confidence increasing vs. knowledge increasing) to send to each individual each day to increase adherence and physical activity. Our results show that ROGUE-UCB performs better in terms of regret and average reward as compared to state of the art algorithms, and the use of ROGUE-UCB increases daily step counts by roughly 1,000 steps a day (about a half-mile more of walking) as compared to other algorithms.
Tasks	Decision Making
Published	2017-07-26
URL	https://arxiv.org/abs/1707.08423v3
PDF	https://arxiv.org/pdf/1707.08423v3.pdf
PWC	https://paperswithcode.com/paper/non-stationary-bandits-with-habituation-and
Repo
Framework

New Reinforcement Learning Using a Chaotic Neural Network for Emergence of “Thinking” - “Exploration” Grows into “Thinking” through Learning -


Title	New Reinforcement Learning Using a Chaotic Neural Network for Emergence of “Thinking” - “Exploration” Grows into “Thinking” through Learning -
Authors	Katsunari Shibata, Yuki Goto
Abstract	Expectation for the emergence of higher functions is getting larger in the framework of end-to-end reinforcement learning using a recurrent neural network. However, the emergence of “thinking” that is a typical higher function is difficult to realize because “thinking” needs non fixed-point, flow-type attractors with both convergence and transition dynamics. Furthermore, in order to introduce “inspiration” or “discovery” in “thinking”, not completely random but unexpected transition should be also required. By analogy to “chaotic itinerancy”, we have hypothesized that “exploration” grows into “thinking” through learning by forming flow-type attractors on chaotic random-like dynamics. It is expected that if rational dynamics are learned in a chaotic neural network (ChNN), coexistence of rational state transition, inspiration-like state transition and also random-like exploration for unknown situation can be realized. Based on the above idea, we have proposed new reinforcement learning using a ChNN as an actor. The positioning of exploration is completely different from the conventional one. The chaotic dynamics inside the ChNN produces exploration factors by itself. Since external random numbers for stochastic action selection are not used, exploration factors cannot be isolated from the output. Therefore, the learning method is also completely different from the conventional one. At each non-feedback connection, one variable named causality trace takes in and maintains the input through the connection according to the change in its output. Using the trace and TD error, the weight is updated. In this paper, as the result of a recent simple task to see whether the new learning works or not, it is shown that a robot with two wheels and two visual sensors reaches a target while avoiding an obstacle after learning though there are still many rooms for improvement.
Tasks
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05551v1
PDF	http://arxiv.org/pdf/1705.05551v1.pdf
PWC	https://paperswithcode.com/paper/new-reinforcement-learning-using-a-chaotic
Repo
Framework

People on Drugs: Credibility of User Statements in Health Communities


Title	People on Drugs: Credibility of User Statements in Health Communities
Authors	Subhabrata Mukherjee, Gerhard Weikum, Cristian Danescu-Niculescu-Mizil
Abstract	Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformation. In this work we propose a method for automatically establishing the credibility of user-generated medical statements and the trustworthiness of their authors by exploiting linguistic cues and distant supervision from expert sources. To this end we introduce a probabilistic graphical model that jointly learns user trustworthiness, statement credibility, and language objectivity. We apply this methodology to the task of extracting rare or unknown side-effects of medical drugs — this being one of the problems where large scale non-expert data has the potential to complement expert medical knowledge. We show that our method can reliably extract side-effects and filter out false statements, while identifying trustworthy users that are likely to contribute valuable medical information.
Tasks
Published	2017-05-06
URL	http://arxiv.org/abs/1705.02522v1
PDF	http://arxiv.org/pdf/1705.02522v1.pdf
PWC	https://paperswithcode.com/paper/people-on-drugs-credibility-of-user
Repo
Framework

Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery


Title	Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery
Authors	Gencer Sumbul, Ramazan Gokberk Cinbis, Selim Aksoy
Abstract	Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised algorithms fail to handle this problem where there is low between-class variance and high within-class variance for the classes of interest with small sample sizes. We study an even more extreme scenario named zero-shot learning (ZSL) in which no training example exists for some of the classes. ZSL aims to build a recognition model for new unseen categories by relating them to seen classes that were previously learned. We establish this relation by learning a compatibility function between image features extracted via a convolutional neural network and auxiliary information that describes the semantics of the classes of interest by using training samples from the seen classes. Then, we show how knowledge transfer can be performed for the unseen classes by maximizing this function during inference. We introduce a new data set that contains 40 different types of street trees in 1-ft spatial resolution aerial data, and evaluate the performance of this model with manually annotated attributes, a natural language model, and a scientific taxonomy as auxiliary information. The experiments show that the proposed model achieves 14.3% recognition accuracy for the classes with no training examples, which is significantly better than a random guess accuracy of 6.3% for 16 test classes, and three other ZSL algorithms.
Tasks	Language Modelling, Object Recognition, Transfer Learning, Zero-Shot Learning
Published	2017-12-09
URL	http://arxiv.org/abs/1712.03323v1
PDF	http://arxiv.org/pdf/1712.03323v1.pdf
PWC	https://paperswithcode.com/paper/fine-grained-object-recognition-and-zero-shot
Repo
Framework

Machine learning for classification and quantification of monoclonal antibody preparations for cancer therapy


Title	Machine learning for classification and quantification of monoclonal antibody preparations for cancer therapy
Authors	Laetitia Le, Camille Marini, Alexandre Gramfort, David Nguyen, Mehdi Cherti, Sana Tfaili, Ali Tfayli, Arlette Baillet-Guffroy, Patrice Prognon, Pierre Chaminade, Eric Caudron, Balázs Kégl
Abstract	Monoclonal antibodies constitute one of the most important strategies to treat patients suffering from cancers such as hematological malignancies and solid tumors. In order to guarantee the quality of those preparations prepared at hospital, quality control has to be developed. The aim of this study was to explore a noninvasive, nondestructive, and rapid analytical method to ensure the quality of the final preparation without causing any delay in the process. We analyzed four mAbs (Inlfiximab, Bevacizumab, Ramucirumab and Rituximab) diluted at therapeutic concentration in chloride sodium 0.9% using Raman spectroscopy. To reduce the prediction errors obtained with traditional chemometric data analysis, we explored a data-driven approach using statistical machine learning methods where preprocessing and predictive models are jointly optimized. We prepared a data analytics workflow and submitted the problem to a collaborative data challenge platform called Rapid Analytics and Model Prototyping (RAMP). This allowed to use solutions from about 300 data scientists during five days of collaborative work. The prediction of the four mAbs samples was considerably improved with a misclassification rate and the mean error rate of 0.8% and 4%, respectively.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07099v2
PDF	http://arxiv.org/pdf/1705.07099v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-classification-and
Repo
Framework

Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks


Title	Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks
Authors	Roby Velez, Jeff Clune
Abstract	A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is when learning new information erases previously learned information. Catastrophic forgetting occurs in artificial neural networks (ANNs), which have fueled most recent advances in AI. A recent paper proposed that catastrophic forgetting in ANNs can be reduced by promoting modularity, which can limit forgetting by isolating task information to specific clusters of nodes and connections (functional modules). While the prior work did show that modular ANNs suffered less from catastrophic forgetting, it was not able to produce ANNs that possessed task-specific functional modules, thereby leaving the main theory regarding modularity and forgetting untested. We introduce diffusion-based neuromodulation, which simulates the release of diffusing, neuromodulatory chemicals within an ANN that can modulate (i.e. up or down regulate) learning in a spatial region. On the simple diagnostic problem from the prior work, diffusion-based neuromodulation 1) induces task-specific learning in groups of nodes and connections (task-specific localized learning), which 2) produces functional modules for each subtask, and 3) yields higher performance by eliminating catastrophic forgetting. Overall, our results suggest that diffusion-based neuromodulation promotes task-specific localized learning and functional modularity, which can help solve the challenging, but important problem of catastrophic forgetting.
Tasks
Published	2017-05-20
URL	http://arxiv.org/abs/1705.07241v3
PDF	http://arxiv.org/pdf/1705.07241v3.pdf
PWC	https://paperswithcode.com/paper/diffusion-based-neuromodulation-can-eliminate
Repo
Framework

Theorem Proving Based on Semantics of DNA Strand Graph


Title	Theorem Proving Based on Semantics of DNA Strand Graph
Authors	Kumar S. Ray, Mandrita Mondal
Abstract	Because of several technological limitations of traditional silicon based computing, for past few years a paradigm shift, from silicon to carbon, is occurring in computational world. DNA computing has been considered to be quite promising in solving computational and reasoning problems by using DNA strands. Resolution, an important aspect of automated theorem proving and mathematical logic, is a rule of inference which leads to proof by contradiction technique for sentences in propositional logic and first-order logic. This can also be called refutation theorem-proving. In this paper we have shown how the theorem proving with resolution refutation by DNA computation can be represented by the semantics of process calculus and strand graph.
Tasks	Automated Theorem Proving
Published	2017-02-15
URL	http://arxiv.org/abs/1702.05383v1
PDF	http://arxiv.org/pdf/1702.05383v1.pdf
PWC	https://paperswithcode.com/paper/theorem-proving-based-on-semantics-of-dna
Repo
Framework

Towards a Crowd Analytic Framework For Crowd Management in Majid-al-Haram


Title	Towards a Crowd Analytic Framework For Crowd Management in Majid-al-Haram
Authors	Sultan Daud Khan, Muhammad Tayyab, Muhammad Khurram Amin, Akram Nour, Anas Basalamah, Saleh Basalamah, Sohaib Ahmad Khan
Abstract	The scared cities of Makkah Al Mukarramah and Madina Al Munawarah host millions of pilgrims every year. During Hajj, the movement of large number of people has a unique spatial and temporal constraints, which makes Hajj one of toughest challenges for crowd management. In this paper, we propose a computer vision based framework that automatically analyses video sequence and computes important measurements which include estimation of crowd density, identification of dominant patterns, detection and localization of congestion. In addition, we analyze helpful statistics of the crowd like speed, and direction, that could provide support to crowd management personnel. The framework presented in this paper indicate that new advances in computer vision and machine learning can be leveraged effectively for challenging and high density crowd management applications. However, significant customization of existing approaches is required to apply them to the challenging crowd management situations in Masjid Al Haram. Our results paint a promising picture for deployment of computer vision technologies to assist in quantitative measurement of crowd size, density and congestion.
Tasks
Published	2017-09-14
URL	http://arxiv.org/abs/1709.05952v1
PDF	http://arxiv.org/pdf/1709.05952v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-crowd-analytic-framework-for-crowd
Repo
Framework

Image classification using local tensor singular value decompositions


Title	Image classification using local tensor singular value decompositions
Authors	Elizabeth Newman, Misha Kilmer, Lior Horesh
Abstract	From linear classifiers to neural networks, image classification has been a widely explored topic in mathematics, and many algorithms have proven to be effective classifiers. However, the most accurate classifiers typically have significantly high storage costs, or require complicated procedures that may be computationally expensive. We present a novel (nonlinear) classification approach using truncation of local tensor singular value decompositions (tSVD) that robustly offers accurate results, while maintaining manageable storage costs. Our approach takes advantage of the optimality of the representation under the tensor algebra described to determine to which class an image belongs. We extend our approach to a method that can determine specific pairwise match scores, which could be useful in, for example, object recognition problems where pose/position are different. We demonstrate the promise of our new techniques on the MNIST data set.
Tasks	Image Classification, Object Recognition
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09693v1
PDF	http://arxiv.org/pdf/1706.09693v1.pdf
PWC	https://paperswithcode.com/paper/image-classification-using-local-tensor
Repo
Framework


Title	SPARCNN: SPAtially Related Convolutional Neural Networks
Authors	JT Turner, Kalyan Moy Gupta, David Aha
Abstract	The ability to accurately detect and classify objects at varying pixel sizes in cluttered scenes is crucial to many Navy applications. However, detection performance of existing state-of the-art approaches such as convolutional neural networks (CNNs) degrade and suffer when applied to such cluttered and multi-object detection tasks. We conjecture that spatial relationships between objects in an image could be exploited to significantly improve detection accuracy, an approach that had not yet been considered by any existing techniques (to the best of our knowledge) at the time the research was conducted. We introduce a detection and classification technique called Spatially Related Detection with Convolutional Neural Networks (SPARCNN) that learns and exploits a probabilistic representation of inter-object spatial configurations within images from training sets for more effective region proposals to use with state-of-the-art CNNs. Our empirical evaluation of SPARCNN on the VOC 2007 dataset shows that it increases classification accuracy by 8% when compared to a region proposal technique that does not exploit spatial relations. More importantly, we obtained a higher performance boost of 18.8% when task difficulty in the test set is increased by including highly obscured objects and increased image clutter.
Tasks	Object Detection
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07522v1
PDF	http://arxiv.org/pdf/1708.07522v1.pdf
PWC	https://paperswithcode.com/paper/sparcnn-spatially-related-convolutional
Repo
Framework

Learning Rich Geographical Representations: Predicting Colorectal Cancer Survival in the State of Iowa


Title	Learning Rich Geographical Representations: Predicting Colorectal Cancer Survival in the State of Iowa
Authors	Michael T. Lash, Yuqi Sun, Xun Zhou, Charles F. Lynch, W. Nick Street
Abstract	Neural networks are capable of learning rich, nonlinear feature representations shown to be beneficial in many predictive tasks. In this work, we use these models to explore the use of geographical features in predicting colorectal cancer survival curves for patients in the state of Iowa, spanning the years 1989 to 2012. Specifically, we compare model performance using a newly defined metric – area between the curves (ABC) – to assess (a) whether survival curves can be reasonably predicted for colorectal cancer patients in the state of Iowa, (b) whether geographical features improve predictive performance, and (c) whether a simple binary representation or richer, spectral clustering-based representation perform better. Our findings suggest that survival curves can be reasonably estimated on average, with predictive performance deviating at the five-year survival mark. We also find that geographical features improve predictive performance, and that the best performance is obtained using richer, spectral analysis-elicited features.
Tasks
Published	2017-08-15
URL	http://arxiv.org/abs/1708.04714v1
PDF	http://arxiv.org/pdf/1708.04714v1.pdf
PWC	https://paperswithcode.com/paper/learning-rich-geographical-representations
Repo
Framework

Deep learning from crowds


Title	Deep learning from crowds
Authors	Filipe Rodrigues, Francisco Pereira
Abstract	Over the last few years, deep learning has revolutionized the field of machine learning by dramatically improving the state-of-the-art in various domains. However, as the size of supervised artificial neural networks grows, typically so does the need for larger labeled datasets. Recently, crowdsourcing has established itself as an efficient and cost-effective solution for labeling large sets of data in a scalable manner, but it often requires aggregating labels from multiple noisy contributors with different levels of expertise. In this paper, we address the problem of learning deep neural networks from crowds. We begin by describing an EM algorithm for jointly learning the parameters of the network and the reliabilities of the annotators. Then, a novel general-purpose crowd layer is proposed, which allows us to train deep neural networks end-to-end, directly from the noisy labels of multiple annotators, using only backpropagation. We empirically show that the proposed approach is able to internally capture the reliability and biases of different annotators and achieve new state-of-the-art results for various crowdsourced datasets across different settings, namely classification, regression and sequence labeling.
Tasks
Published	2017-09-06
URL	http://arxiv.org/abs/1709.01779v2
PDF	http://arxiv.org/pdf/1709.01779v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-from-crowds
Repo
Framework

Learning and inference in knowledge-based probabilistic model for medical diagnosis


Title	Learning and inference in knowledge-based probabilistic model for medical diagnosis
Authors	Jingchi Jiang, Chao Zhao, Yi Guan, Qiubin Yu
Abstract	Based on a weighted knowledge graph to represent first-order knowledge and combining it with a probabilistic model, we propose a methodology for the creation of a medical knowledge network (MKN) in medical diagnosis. When a set of symptoms is activated for a specific patient, we can generate a ground medical knowledge network composed of symptom nodes and potential disease nodes. By Incorporating a Boltzmann machine into the potential function of a Markov network, we investigated the joint probability distribution of the MKN. In order to deal with numerical symptoms, a multivariate inference model is presented that uses conditional probability. In addition, the weights for the knowledge graph were efficiently learned from manually annotated Chinese Electronic Medical Records (CEMRs). In our experiments, we found numerically that the optimum choice of the quality of disease node and the expression of symptom variable can improve the effectiveness of medical diagnosis. Our experimental results comparing a Markov logic network and the logistic regression algorithm on an actual CEMR database indicate that our method holds promise and that MKN can facilitate studies of intelligent diagnosis.
Tasks	Medical Diagnosis
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09368v1
PDF	http://arxiv.org/pdf/1703.09368v1.pdf
PWC	https://paperswithcode.com/paper/learning-and-inference-in-knowledge-based
Repo
Framework