July 27, 2019

3083 words 15 mins read

Paper Group ANR 596

Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images. Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution. Direct Estimation of Regional Wall Thicknesses via Residual Recurrent Neural Network. Hierarc …

Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images


Title	Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images
Authors	Donghuan Lu, Karteek Popuri, Weiguang Ding, Rakesh Balachandar, Mirza Faisal Beg
Abstract	Alzheimer’s Disease (AD) is a progressive neurodegenerative disease. Amnestic mild cognitive impairment (MCI) is a common first symptom before the conversion to clinical impairment where the individual becomes unable to perform activities of daily living independently. Although there is currently no treatment available, the earlier a conclusive diagnosis is made, the earlier the potential for interventions to delay or perhaps even prevent progression to full-blown AD. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo view into the structure and function (glucose metabolism) of the living brain. It is hypothesized that combining different image modalities could better characterize the change of human brain and result in a more accuracy early diagnosis of AD. In this paper, we proposed a novel framework to discriminate normal control(NC) subjects from subjects with AD pathology (AD and NC, MCI subjects convert to AD in future). Our novel approach utilizing a multimodal and multiscale deep neural network was found to deliver a 85.68% accuracy in the prediction of subjects within 3 years to conversion. Cross validation experiments proved that it has better discrimination ability compared with results in existing published literature.
Tasks
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04782v1
PDF	http://arxiv.org/pdf/1710.04782v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-and-multiscale-deep-neural
Repo
Framework

Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution


Title	Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution
Authors	Dwarikanath Mahapatra, Behzad Bozorgtabar
Abstract	We propose an image super resolution(ISR) method using generative adversarial networks (GANs) that takes a low resolution input fundus image and generates a high resolution super resolved (SR) image upto scaling factor of $16$. This facilitates more accurate automated image analysis, especially for small or blurred landmarks and pathologies. Local saliency maps, which define each pixel’s importance, are used to define a novel saliency loss in the GAN cost function. Experimental results show the resulting SR images have perceptual quality very close to the original images and perform better than competing methods that do not weigh pixels according to their importance. When used for retinal vasculature segmentation, our SR images result in accuracy levels close to those obtained when using the original images.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04783v3
PDF	http://arxiv.org/pdf/1710.04783v3.pdf
PWC	https://paperswithcode.com/paper/retinal-vasculature-segmentation-using-local
Repo
Framework

Direct Estimation of Regional Wall Thicknesses via Residual Recurrent Neural Network


Title	Direct Estimation of Regional Wall Thicknesses via Residual Recurrent Neural Network
Authors	Wufeng Xue, Ilanit Ben Nachum, Sachin Pandey, James Warrington, Stephanie Leung, Shuo Li
Abstract	Accurate estimation of regional wall thicknesses (RWT) of left ventricular (LV) myocardium from cardiac MR sequences is of significant importance for identification and diagnosis of cardiac disease. Existing RWT estimation still relies on segmentation of LV myocardium, which requires strong prior information and user interaction. No work has been devoted into direct estimation of RWT from cardiac MR images due to the diverse shapes and structures for various subjects and cardiac diseases, as well as the complex regional deformation of LV myocardium during the systole and diastole phases of the cardiac cycle. In this paper, we present a newly proposed Residual Recurrent Neural Network (ResRNN) that fully leverages the spatial and temporal dynamics of LV myocardium to achieve accurate frame-wise RWT estimation. Our ResRNN comprises two paths: 1) a feed forward convolution neural network (CNN) for effective and robust CNN embedding learning of various cardiac images and preliminary estimation of RWT from each frame itself independently, and 2) a recurrent neural network (RNN) for further improving the estimation by modeling spatial and temporal dynamics of LV myocardium. For the RNN path, we design for cardiac sequences a Circle-RNN to eliminate the effect of null hidden input for the first time-step. Our ResRNN is capable of obtaining accurate estimation of cardiac RWT with Mean Absolute Error of 1.44mm (less than 1-pixel error) when validated on cardiac MR sequences of 145 subjects, evidencing its great potential in clinical cardiac function assessment.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09728v1
PDF	http://arxiv.org/pdf/1705.09728v1.pdf
PWC	https://paperswithcode.com/paper/direct-estimation-of-regional-wall
Repo
Framework

Hierarchical Clustering: Objective Functions and Algorithms


Title	Hierarchical Clustering: Objective Functions and Algorithms
Authors	Vincent Cohen-Addad, Varun Kanade, Frederik Mallmann-Trenn, Claire Mathieu
Abstract	Hierarchical clustering is a recursive partitioning of a dataset into clusters at an increasingly finer granularity. Motivated by the fact that most work on hierarchical clustering was based on providing algorithms, rather than optimizing a specific objective, Dasgupta framed similarity-based hierarchical clustering as a combinatorial optimization problem, where a `good' hierarchical clustering is one that minimizes some cost function. He showed that this cost function has certain desirable properties. We take an axiomatic approach to defining` good’ objective functions for both similarity and dissimilarity-based hierarchical clustering. We characterize a set of “admissible” objective functions (that includes Dasgupta’s one) that have the property that when the input admits a natural' hierarchical clustering, it has an optimal value. Equipped with a suitable objective function, we analyze the performance of practical algorithms, as well as develop better algorithms. For similarity-based hierarchical clustering, Dasgupta showed that the divisive sparsest-cut approach achieves an $O(\log^{3/2} n)$-approximation. We give a refined analysis of the algorithm and show that it in fact achieves an $O(\sqrt{\log n})$-approx. (Charikar and Chatziafratis independently proved that it is a $O(\sqrt{\log n})$-approx.). This improves upon the LP-based $O(\log n)$-approx. of Roy and Pokutta. For dissimilarity-based hierarchical clustering, we show that the classic average-linkage algorithm gives a factor 2 approx., and provide a simple and better algorithm that gives a factor 3/2 approx.. Finally, we consider beyond-worst-case’ scenario through a generalisation of the stochastic block model for hierarchical clustering. We show that Dasgupta’s cost function has desirable properties for these inputs and we provide a simple 1 + o(1)-approximation in this setting.
Tasks	Combinatorial Optimization
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02147v1
PDF	http://arxiv.org/pdf/1704.02147v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-clustering-objective-functions
Repo
Framework

Using GPI-2 for Distributed Memory Paralleliziation of the Caffe Toolbox to Speed up Deep Neural Network Training


Title	Using GPI-2 for Distributed Memory Paralleliziation of the Caffe Toolbox to Speed up Deep Neural Network Training
Authors	Martin Kuehn, Janis Keuper, Franz-Josef Pfreundt
Abstract	Deep Neural Network (DNN) are currently of great inter- est in research and application. The training of these net- works is a compute intensive and time consuming task. To reduce training times to a bearable amount at reasonable cost we extend the popular Caffe toolbox for DNN with an efficient distributed memory communication pattern. To achieve good scalability we emphasize the overlap of computation and communication and prefer fine granu- lar synchronization patterns over global barriers. To im- plement these communication patterns we rely on the the Global address space Programming Interface version 2 (GPI-2) communication library. This interface provides a light-weight set of asynchronous one-sided communica- tion primitives supplemented by non-blocking fine gran- ular data synchronization mechanisms. Therefore, Caf- feGPI is the name of our parallel version of Caffe. First benchmarks demonstrate better scaling behavior com- pared with other extensions, e.g., the Intel TM Caffe. Even within a single symmetric multiprocessing machine with four graphics processing units, the CaffeGPI scales bet- ter than the standard Caffe toolbox. These first results demonstrate that the use of standard High Performance Computing (HPC) hardware is a valid cost saving ap- proach to train large DDNs. I/O is an other bottleneck to work with DDNs in a standard parallel HPC setting, which we will consider in more detail in a forthcoming paper.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1706.00095v2
PDF	http://arxiv.org/pdf/1706.00095v2.pdf
PWC	https://paperswithcode.com/paper/using-gpi-2-for-distributed-memory
Repo
Framework

Cross-lingual Speaker Verification with Deep Feature Learning


Title	Cross-lingual Speaker Verification with Deep Feature Learning
Authors	Lantian Li, Dong Wang, Askar Rozi, Thomas Fang Zheng
Abstract	Existing speaker verification (SV) systems often suffer from performance degradation if there is any language mismatch between model training, speaker enrollment, and test. A major cause of this degradation is that most existing SV methods rely on a probabilistic model to infer the speaker factor, so any significant change on the distribution of the speech signal will impact the inference. Recently, we proposed a deep learning model that can learn how to extract the speaker factor by a deep neural network (DNN). By this feature learning, an SV system can be constructed with a very simple back-end model. In this paper, we investigate the robustness of the feature-based SV system in situations with language mismatch. Our experiments were conducted on a complex cross-lingual scenario, where the model training was in English, and the enrollment and test were in Chinese or Uyghur. The experiments demonstrated that the feature-based system outperformed the i-vector system with a large margin, particularly with language mismatch between enrollment and test.
Tasks	Speaker Verification
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07861v1
PDF	http://arxiv.org/pdf/1706.07861v1.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-speaker-verification-with-deep
Repo
Framework

Extracting Bilingual Persian Italian Lexicon from Comparable Corpora Using Different Types of Seed Dictionaries


Title	Extracting Bilingual Persian Italian Lexicon from Comparable Corpora Using Different Types of Seed Dictionaries
Authors	Ebrahim Ansari, M. H. Sadreddini, Lucio Grandinetti, Mahsa Radinmehr, Ziba Khosravan, Mehdi Sheikhalishahi
Abstract	Bilingual dictionaries are very important in various fields of natural language processing. In recent years, research on extracting new bilingual lexicons from non-parallel (comparable) corpora have been proposed. Almost all use a small existing dictionary or other resources to make an initial list called the “seed dictionary”. In this paper, we discuss the use of different types of dictionaries as the initial starting list for creating a bilingual Persian-Italian lexicon from a comparable corpus. Our experiments apply state-of-the-art techniques on three different seed dictionaries; an existing dictionary, a dictionary created with pivot-based schema, and a dictionary extracted from a small Persian-Italian parallel text. The interesting challenge of our approach is to find a way to combine different dictionaries together in order to produce a better and more accurate lexicon. In order to combine seed dictionaries, we propose two different combination models and examine the effect of our novel combination models on various comparable corpora that have differing degrees of comparability. We conclude with a proposal for a new weighting system to improve the extracted lexicon. The experimental results produced by our implementation show the efficiency of our proposed models.
Tasks
Published	2017-01-29
URL	https://arxiv.org/abs/1701.08340v2
PDF	https://arxiv.org/pdf/1701.08340v2.pdf
PWC	https://paperswithcode.com/paper/extracting-bilingual-persian-italian-lexicon
Repo
Framework

Efficient Approximate Solutions to Mutual Information Based Global Feature Selection


Title	Efficient Approximate Solutions to Mutual Information Based Global Feature Selection
Authors	Hemanth Venkateswara, Prasanth Lade, Binbin Lin, Jieping Ye, Sethuraman Panchanathan
Abstract	Mutual Information (MI) is often used for feature selection when developing classifier models. Estimating the MI for a subset of features is often intractable. We demonstrate, that under the assumptions of conditional independence, MI between a subset of features can be expressed as the Conditional Mutual Information (CMI) between pairs of features. But selecting features with the highest CMI turns out to be a hard combinatorial problem. In this work, we have applied two unique global methods, Truncated Power Method (TPower) and Low Rank Bilinear Approximation (LowRank), to solve the feature selection problem. These algorithms provide very good approximations to the NP-hard CMI based feature selection problem. We experimentally demonstrate the effectiveness of these procedures across multiple datasets and compare them with existing MI based global and iterative feature selection procedures.
Tasks	Feature Selection
Published	2017-06-23
URL	http://arxiv.org/abs/1706.07535v1
PDF	http://arxiv.org/pdf/1706.07535v1.pdf
PWC	https://paperswithcode.com/paper/efficient-approximate-solutions-to-mutual
Repo
Framework

A New Spectral Clustering Algorithm


Title	A New Spectral Clustering Algorithm
Authors	W. R. Casper, Balu Nadiga
Abstract	We present a new clustering algorithm that is based on searching for natural gaps in the components of the lowest energy eigenvectors of the Laplacian of a graph. In comparing the performance of the proposed method with a set of other popular methods (KMEANS, spectral-KMEANS, and an agglomerative method) in the context of the Lancichinetti-Fortunato-Radicchi (LFR) Benchmark for undirected weighted overlapping networks, we find that the new method outperforms the other spectral methods considered in certain parameter regimes. Finally, in an application to climate data involving one of the most important modes of interannual climate variability, the El Nino Southern Oscillation phenomenon, we demonstrate the ability of the new algorithm to readily identify different flavors of the phenomenon.
Tasks
Published	2017-10-07
URL	http://arxiv.org/abs/1710.02756v1
PDF	http://arxiv.org/pdf/1710.02756v1.pdf
PWC	https://paperswithcode.com/paper/a-new-spectral-clustering-algorithm
Repo
Framework

EmojiNet: An Open Service and API for Emoji Sense Discovery


Title	EmojiNet: An Open Service and API for Emoji Sense Discovery
Authors	Sanjaya Wijeratne, Lakshika Balasuriya, Amit Sheth, Derek Doran
Abstract	This paper presents the release of EmojiNet, the largest machine-readable emoji sense inventory that links Unicode emoji representations to their English meanings extracted from the Web. EmojiNet is a dataset consisting of: (i) 12,904 sense labels over 2,389 emoji, which were extracted from the web and linked to machine-readable sense definitions seen in BabelNet, (ii) context words associated with each emoji sense, which are inferred through word embedding models trained over Google News corpus and a Twitter message corpus for each emoji sense definition, and (iii) recognizing discrepancies in the presentation of emoji on different platforms, specification of the most likely platform-based emoji sense for a selected set of emoji. The dataset is hosted as an open service with a REST API and is available at http://emojinet.knoesis.org/. The development of this dataset, evaluation of its quality, and its applications including emoji sense disambiguation and emoji sense similarity are discussed.
Tasks
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04652v1
PDF	http://arxiv.org/pdf/1707.04652v1.pdf
PWC	https://paperswithcode.com/paper/emojinet-an-open-service-and-api-for-emoji
Repo
Framework

LoIDE: a web-based IDE for Logic Programming - Preliminary Technical Report


Title	LoIDE: a web-based IDE for Logic Programming - Preliminary Technical Report
Authors	Stefano Germano, Francesco Calimeri, Eliana Palermiti
Abstract	Logic-based paradigms are nowadays widely used in many different fields, also thank to the availability of robust tools and systems that allow the development of real-world and industrial applications. In this work we present LoIDE, an advanced and modular web-editor for logic-based languages that also integrates with state-of-the-art solvers.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05341v1
PDF	http://arxiv.org/pdf/1709.05341v1.pdf
PWC	https://paperswithcode.com/paper/loide-a-web-based-ide-for-logic-programming
Repo
Framework

Corrupt Bandits for Preserving Local Privacy


Title	Corrupt Bandits for Preserving Local Privacy
Authors	Pratik Gajane, Tanguy Urvoy, Emilie Kaufmann
Abstract	We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender systems, the goal is to maximize the sum of the (unobserved) rewards, based on the observation of transformation of these rewards through a stochastic corruption process with known parameters. We provide a lower bound on the expected regret of any bandit algorithm in this corrupted setting. We devise a frequentist algorithm, KLUCB-CF, and a Bayesian algorithm, TS-CF and give upper bounds on their regret. We also provide the appropriate corruption parameters to guarantee a desired level of local privacy and analyze how this impacts the regret. Finally, we present some experimental results that confirm our analysis.
Tasks	Recommendation Systems
Published	2017-08-16
URL	http://arxiv.org/abs/1708.05033v2
PDF	http://arxiv.org/pdf/1708.05033v2.pdf
PWC	https://paperswithcode.com/paper/corrupt-bandits-for-preserving-local-privacy
Repo
Framework

Compiling quantum circuits to realistic hardware architectures using temporal planners


Title	Compiling quantum circuits to realistic hardware architectures using temporal planners
Authors	Davide Venturelli, Minh Do, Eleanor Rieffel, Jeremy Frank
Abstract	To run quantum algorithms on emerging gate-model quantum hardware, quantum circuits must be compiled to take into account constraints on the hardware. For near-term hardware, with only limited means to mitigate decoherence, it is critical to minimize the duration of the circuit. We investigate the application of temporal planners to the problem of compiling quantum circuits to newly emerging quantum hardware. While our approach is general, we focus on compiling to superconducting hardware architectures with nearest neighbor constraints. Our initial experiments focus on compiling Quantum Alternating Operator Ansatz (QAOA) circuits whose high number of commuting gates allow great flexibility in the order in which the gates can be applied. That freedom makes it more challenging to find optimal compilations but also means there is a greater potential win from more optimized compilation than for less flexible circuits. We map this quantum circuit compilation problem to a temporal planning problem, and generated a test suite of compilation problems for QAOA circuits of various sizes to a realistic hardware architecture. We report compilation results from several state-of-the-art temporal planners on this test set. This early empirical evaluation demonstrates that temporal planning is a viable approach to quantum circuit compilation.
Tasks
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08927v2
PDF	http://arxiv.org/pdf/1705.08927v2.pdf
PWC	https://paperswithcode.com/paper/compiling-quantum-circuits-to-realistic
Repo
Framework

Emotion Recognition From Speech With Recurrent Neural Networks


Title	Emotion Recognition From Speech With Recurrent Neural Networks
Authors	Vladimir Chernykh, Pavel Prikhodko
Abstract	In this paper the task of emotion recognition from speech is considered. Proposed approach uses deep recurrent neural network trained on a sequence of acoustic features calculated over small speech intervals. At the same time special probabilistic-nature CTC loss function allows to consider long utterances containing both emotional and neutral parts. The effectiveness of such an approach is shown in two ways. Firstly, the comparison with recent advances in this field is carried out. Secondly, human performance on the same task is measured. Both criteria show the high quality of the proposed method.
Tasks	Emotion Recognition
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08071v2
PDF	http://arxiv.org/pdf/1701.08071v2.pdf
PWC	https://paperswithcode.com/paper/emotion-recognition-from-speech-with
Repo
Framework

Identifying Growth-Patterns in Children by Applying Cluster analysis to Electronic Medical Records


Title	Identifying Growth-Patterns in Children by Applying Cluster analysis to Electronic Medical Records
Authors	Moumita Bhattacharya, Deborah Ehrenthal, Hagit Shatkay
Abstract	Obesity is one of the leading health concerns in the United States. Researchers and health care providers are interested in understanding factors affecting obesity and detecting the likelihood of obesity as early as possible. In this paper, we set out to recognize children who have higher risk of obesity by identifying distinct growth patterns in them. This is done by using clustering methods, which group together children who share similar body measurements over a period of time. The measurements characterizing children within the same cluster are plotted as a function of age. We refer to these plots as growthpattern curves. We show that distinct growth-pattern curves are associated with different clusters and thus can be used to separate children into the topmost (heaviest), middle, or bottom-most cluster based on early growth measurements.
Tasks
Published	2017-08-16
URL	http://arxiv.org/abs/1708.07058v1
PDF	http://arxiv.org/pdf/1708.07058v1.pdf
PWC	https://paperswithcode.com/paper/identifying-growth-patterns-in-children-by
Repo
Framework