October 16, 2019

3007 words 15 mins read

Paper Group ANR 1096

Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI. On Lebesgue Integral Quadrature. A User-based Visual Analytics Workflow for Exploratory Model Analysis. The USTC-NEL Speech Translation system at IWSLT 2018. Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines. Psychological State in Text: A Limitation …

Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI


Title	Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI
Authors	Xiaoxiao Li, Nicha C. Dvornek, Juntang Zhuang, Pamela Ventola, James S. Duncan
Abstract	Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder. Finding the biomarkers associated with ASD is extremely helpful to understand the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. Although Deep Neural Networks (DNNs) have been applied in functional magnetic resonance imaging (fMRI) to identify ASD, understanding the data-driven computational decision making procedure has not been previously explored. Therefore, in this work, we address the problem of interpreting reliable biomarkers associated with identifying ASD; specifically, we propose a 2-stage method that classifies ASD and control subjects using fMRI images and interprets the saliency features activated by the classifier. First, we trained an accurate DNN classifier. Then, for detecting the biomarkers, different from the DNN visualization works in computer vision, we take advantage of the anatomical structure of brain fMRI and develop a frequency-normalized sampling method to corrupt images. Furthermore, in the ASD vs. control subjects classification scenario, we provide a new approach to detect and characterize important brain features into three categories. The biomarkers we found by the proposed method are robust and consistent with previous findings in the literature. We also validate the detected biomarkers by neurological function decoding and comparing with the DNN activation maps.
Tasks	Decision Making
Published	2018-08-23
URL	http://arxiv.org/abs/1808.08296v1
PDF	http://arxiv.org/pdf/1808.08296v1.pdf
PWC	https://paperswithcode.com/paper/brain-biomarker-interpretation-in-asd-using
Repo
Framework

On Lebesgue Integral Quadrature


Title	On Lebesgue Integral Quadrature
Authors	Vladislav Gennadievich Malyshkin
Abstract	A new type of quadrature is developed. The Gaussian quadrature, for a given measure, finds optimal values of a function’s argument (nodes) and the corresponding weights. In contrast, the Lebesgue quadrature developed in this paper, finds optimal values of function (value-nodes) and the corresponding weights. The Gaussian quadrature groups sums by function argument; it can be viewed as a $n$-point discrete measure, producing the Riemann integral. The Lebesgue quadrature groups sums by function value; it can be viewed as a $n$-point discrete distribution, producing the Lebesgue integral. Mathematically, the problem is reduced to a generalized eigenvalue problem: Lebesgue quadrature value-nodes are the eigenvalues and the corresponding weights are the square of the averaged eigenvectors. A numerical estimation of an integral as the Lebesgue integral is especially advantageous when analyzing irregular and stochastic processes. The approach separates the outcome (value-nodes) and the probability of the outcome (weight). For this reason, it is especially well-suited for the study of non-Gaussian processes. The software implementing the theory is available from the authors.
Tasks	Gaussian Processes
Published	2018-07-17
URL	https://arxiv.org/abs/1807.06007v6
PDF	https://arxiv.org/pdf/1807.06007v6.pdf
PWC	https://paperswithcode.com/paper/on-lebesgue-integral-quadrature
Repo
Framework

A User-based Visual Analytics Workflow for Exploratory Model Analysis


Title	A User-based Visual Analytics Workflow for Exploratory Model Analysis
Authors	Dylan Cashman, Shah Rukh Humayoun, Florian Heimerl, Kendall Park, Subhajit Das, John Thompson, Bahador Saket, Abigail Mosca, John Stasko, Alex Endert, Michael Gleicher, Remco Chang
Abstract	Many visual analytics systems allow users to interact with machine learning models towards the goals of data exploration and insight generation on a given dataset. However, in some situations, insights may be less important than the production of an accurate predictive model for future use. In that case, users are more interested in generating of diverse and robust predictive models, verifying their performance on holdout data, and selecting the most suitable model for their usage scenario. In this paper, we consider the concept of Exploratory Model Analysis (EMA), which is defined as the process of discovering and selecting relevant models that can be used to make predictions on a data source. We delineate the differences between EMA and the well-known term exploratory data analysis in terms of the desired outcome of the analytic process: insights into the data or a set of deployable models. The contributions of this work are a visual analytics system workflow for EMA, a user study, and two use cases validating the effectiveness of the workflow. We found that our system workflow enabled users to generate complex models, to assess them for various qualities, and to select the most relevant model for their task.
Tasks	AutoML, Model Selection
Published	2018-09-27
URL	https://arxiv.org/abs/1809.10782v3
PDF	https://arxiv.org/pdf/1809.10782v3.pdf
PWC	https://paperswithcode.com/paper/visual-analytics-for-automated-model
Repo
Framework

The USTC-NEL Speech Translation system at IWSLT 2018


Title	The USTC-NEL Speech Translation system at IWSLT 2018
Authors	Dan Liu, Junhua Liu, Wu Guo, Shifu Xiong, Zhiqiang Ma, Rui Song, Chongliang Wu, Quan Liu
Abstract	This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech recognition, post-processing and machine translation. We train a group of hybrid-HMM models for our speech recognition, and for machine translation we train transformer based neural machine translation models with speech recognition output style text as input. Experiments conducted on the IWSLT 2018 task indicate that, compared to baseline system from KIT, our system achieved 14.9 BLEU improvement.
Tasks	Machine Translation, Speech Recognition
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02455v1
PDF	http://arxiv.org/pdf/1812.02455v1.pdf
PWC	https://paperswithcode.com/paper/the-ustc-nel-speech-translation-system-at
Repo
Framework

Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines


Title	Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines
Authors	Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M Bayen, Sham Kakade, Igor Mordatch, Pieter Abbeel
Abstract	Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent baseline for variance reduction which fully exploits the structural form of the stochastic policy itself and does not make any additional assumptions about the MDP. We demonstrate and quantify the benefit of the action-dependent baseline through both theoretical analysis as well as numerical results, including an analysis of the suboptimality of the optimal state-dependent baseline. The result is a computationally efficient policy gradient algorithm, which scales to high-dimensional control problems, as demonstrated by a synthetic 2000-dimensional target matching task. Our experimental results indicate that action-dependent baselines allow for faster learning on standard reinforcement learning benchmarks and high-dimensional hand manipulation and synthetic tasks. Finally, we show that the general idea of including additional information in baselines for improved variance reduction can be extended to partially observed and multi-agent tasks.
Tasks	Policy Gradient Methods
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07246v1
PDF	http://arxiv.org/pdf/1803.07246v1.pdf
PWC	https://paperswithcode.com/paper/variance-reduction-for-policy-gradient-with
Repo
Framework

Psychological State in Text: A Limitation of Sentiment Analysis


Title	Psychological State in Text: A Limitation of Sentiment Analysis
Authors	Hwiyeol Jo, Jeong Ryu
Abstract	Starting with the idea that sentiment analysis models should be able to predict not only positive or negative but also other psychological states of a person, we implement a sentiment analysis model to investigate the relationship between the model and emotional state. We first examine psychological measurements of 64 participants and ask them to write a book report about a story. After that, we train our sentiment analysis model using crawled movie review data. We finally evaluate participants’ writings, using the pretrained model as a concept of transfer learning. The result shows that sentiment analysis model performs good at predicting a score, but the score does not have any correlation with human’s self-checked sentiment.
Tasks	Sentiment Analysis, Transfer Learning
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00754v1
PDF	http://arxiv.org/pdf/1806.00754v1.pdf
PWC	https://paperswithcode.com/paper/psychological-state-in-text-a-limitation-of
Repo
Framework

Adaptive Three Operator Splitting


Title	Adaptive Three Operator Splitting
Authors	Fabian Pedregosa, Gauthier Gidel
Abstract	We propose and analyze an adaptive step-size variant of the Davis-Yin three operator splitting. This method can solve optimization problems composed by a sum of a smooth term for which we have access to its gradient and an arbitrary number of potentially non-smooth terms for which we have access to their proximal operator. The proposed method sets the step-size based on local information of the objective –hence allowing for larger step-sizes–, only requires two extra function evaluations per iteration and does not depend on any step-size hyperparameter besides an initial estimate. We provide an iteration complexity analysis that matches the best known results for the non-adaptive variant: sublinear convergence for general convex functions and linear convergence under strong convexity of the smooth term and smoothness of one of the proximal terms. Finally, an empirical comparison with related methods on 6 different problems illustrates the computational advantage of the proposed method.
Tasks
Published	2018-04-06
URL	http://arxiv.org/abs/1804.02339v3
PDF	http://arxiv.org/pdf/1804.02339v3.pdf
PWC	https://paperswithcode.com/paper/adaptive-three-operator-splitting
Repo
Framework

From BoW to CNN: Two Decades of Texture Representation for Texture Classification


Title	From BoW to CNN: Two Decades of Texture Representation for Texture Classification
Authors	Li Liu, Jie Chen, Paul Fieguth, Guoying Zhao, Rama Chellappa, Matti Pietikainen
Abstract	Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention. Since 2000, texture representations based on Bag of Words (BoW) and on Convolutional Neural Networks (CNNs) have been extensively studied with impressive performance. Given this period of remarkable evolution, this paper aims to present a comprehensive survey of advances in texture representation over the last two decades. More than 200 major publications are cited in this survey covering different aspects of the research, which includes (i) problem description; (ii) recent advances in the broad categories of BoW-based, CNN-based and attribute-based methods; and (iii) evaluation issues, specifically benchmark datasets and state of the art results. In retrospect of what has been achieved so far, the survey discusses open challenges and directions for future research.
Tasks	Texture Classification
Published	2018-01-31
URL	http://arxiv.org/abs/1801.10324v2
PDF	http://arxiv.org/pdf/1801.10324v2.pdf
PWC	https://paperswithcode.com/paper/from-bow-to-cnn-two-decades-of-texture
Repo
Framework

Hide and Seek tracker: Real-time recovery from target loss


Title	Hide and Seek tracker: Real-time recovery from target loss
Authors	Alessandro Bay, Panagiotis Sidiropoulos, Eduard Vazquez, Michele Sasdelli
Abstract	In this paper, we examine the real-time recovery of a video tracker from a target loss, using information that is already available from the original tracker and without a significant computational overhead. More specifically, before using the tracker output to update the target position we estimate the detection confidence. In the case of a low confidence, the position update is rejected and the tracker passes to a single-frame failure mode, during which the patch low-level visual content is used to swiftly update the object position, before recovering from the target loss in the next frame. Orthogonally to this improvement, we further enhance the running average method used for creating the query model in tracking-through-similarity. The experimental evidence provided by evaluation on standard tracking datasets (OTB-50, OTB-100 and OTB-2013) validate that target recovery can be successfully achieved without compromising the real-time update of the target position.
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07844v1
PDF	http://arxiv.org/pdf/1806.07844v1.pdf
PWC	https://paperswithcode.com/paper/hide-and-seek-tracker-real-time-recovery-from
Repo
Framework

Online Compact Convexified Factorization Machine


Title	Online Compact Convexified Factorization Machine
Authors	Wenpeng Zhang, Xiao Lin, Peilin Zhao
Abstract	Factorization Machine (FM) is a supervised learning approach with a powerful capability of feature engineering. It yields state-of-the-art performance in various batch learning tasks where all the training data is made available prior to the training. However, in real-world applications where the data arrives sequentially in a streaming manner, the high cost of re-training with batch learning algorithms has posed formidable challenges in the online learning scenario. The initial challenge is that no prior formulations of FM could fulfill the requirements in Online Convex Optimization (OCO) – the paramount framework for online learning algorithm design. To address the aforementioned challenge, we invent a new convexification scheme leading to a Compact Convexified FM (CCFM) that seamlessly meets the requirements in OCO. However for learning Compact Convexified FM (CCFM) in the online learning setting, most existing algorithms suffer from expensive projection operations. To address this subsequent challenge, we follow the general projection-free algorithmic framework of Online Conditional Gradient and propose an Online Compact Convex Factorization Machine (OCCFM) algorithm that eschews the projection operation with efficient linear optimization steps. In support of the proposed OCCFM in terms of its theoretical foundation, we prove that the developed algorithm achieves a sub-linear regret bound. To evaluate the empirical performance of OCCFM, we conduct extensive experiments on 6 real-world datasets for online recommendation and binary classification tasks. The experimental results show that OCCFM outperforms the state-of-art online learning algorithms.
Tasks	Feature Engineering
Published	2018-02-05
URL	http://arxiv.org/abs/1802.01379v1
PDF	http://arxiv.org/pdf/1802.01379v1.pdf
PWC	https://paperswithcode.com/paper/online-compact-convexified-factorization
Repo
Framework

Learning Compact Neural Networks with Regularization


Title	Learning Compact Neural Networks with Regularization
Authors	Samet Oymak
Abstract	Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow neural networks. Our framework is general and covers weight-sharing (convolutional networks), sparsity (network pruning), and low-rank constraints among others. We first introduce covering dimension to quantify the complexity of the constraint set and provide insights on the generalization properties. Then, we show that proposed algorithms become well-behaved and local linear convergence occurs once the amount of data exceeds the covering dimension. Overall, our results demonstrate that near-optimal sample complexity is sufficient for efficient learning and illustrate how regularization can be beneficial to learn over-parameterized networks.
Tasks	Network Pruning
Published	2018-02-05
URL	http://arxiv.org/abs/1802.01223v2
PDF	http://arxiv.org/pdf/1802.01223v2.pdf
PWC	https://paperswithcode.com/paper/learning-compact-neural-networks-with
Repo
Framework

Estimation of Markov Chain via Rank-Constrained Likelihood


Title	Estimation of Markov Chain via Rank-Constrained Likelihood
Authors	Xudong Li, Mengdi Wang, Anru Zhang
Abstract	This paper studies the estimation of low-rank Markov chains from empirical trajectories. We propose a non-convex estimator based on rank-constrained likelihood maximization. Statistical upper bounds are provided for the Kullback-Leiber divergence and the $\ell_2$ risk between the estimator and the true transition matrix. The estimator reveals a compressed state space of the Markov chain. We also develop a novel DC (difference of convex function) programming algorithm to tackle the rank-constrained non-smooth optimization problem. Convergence results are established. Experiments show that the proposed estimator achieves better empirical performance than other popular approaches.
Tasks
Published	2018-04-03
URL	http://arxiv.org/abs/1804.00795v2
PDF	http://arxiv.org/pdf/1804.00795v2.pdf
PWC	https://paperswithcode.com/paper/estimation-of-markov-chain-via-rank
Repo
Framework

ISEC: Iterative over-Segmentation via Edge Clustering


Title	ISEC: Iterative over-Segmentation via Edge Clustering
Authors	Marcelo Santos, Luciano Oliveira
Abstract	Several image pattern recognition tasks rely on superpixel generation as a fundamental step. Image analysis based on superpixels facilitates domain-specific applications, also speeding up the overall processing time of the task. Recent superpixel methods have been designed to fit boundary adherence, usually regulating the size and shape of each superpixel in order to mitigate the occurrence of undersegmentation failures. Superpixel regularity and compactness sometimes imposes an excessive number of segments in the image, which ultimately decreases the efficiency of the final segmentation, specially in video segmentation. We propose here a novel method to generate superpixels, called iterative over-segmentation via edge clustering (ISEC), which addresses the over-segmentation problem from a different perspective in contrast to recent state-of-the-art approaches. ISEC iteratively clusters edges extracted from the image objects, providing adaptive superpixels in size, shape and quantity, while preserving suitable adherence to the real object boundaries. All this is achieved at a very low computational cost. Experiments show that ISEC stands out from existing methods, meeting a favorable balance between segmentation stability and accurate representation of motion discontinuities, which are features specially suitable to video segmentation.
Tasks	Video Semantic Segmentation
Published	2018-02-16
URL	http://arxiv.org/abs/1802.05816v1
PDF	http://arxiv.org/pdf/1802.05816v1.pdf
PWC	https://paperswithcode.com/paper/isec-iterative-over-segmentation-via-edge
Repo
Framework

Meshed Up: Learnt Error Correction in 3D Reconstructions


Title	Meshed Up: Learnt Error Correction in 3D Reconstructions
Authors	Michael Tanner, Stefan Saftescu, Alex Bewley, Paul Newman
Abstract	Dense reconstructions often contain errors that prior work has so far minimised using high quality sensors and regularising the output. Nevertheless, errors still persist. This paper proposes a machine learning technique to identify errors in three dimensional (3D) meshes. Beyond simply identifying errors, our method quantifies both the magnitude and the direction of depth estimate errors when viewing the scene. This enables us to improve the reconstruction accuracy. We train a suitably deep network architecture with two 3D meshes: a high-quality laser reconstruction, and a lower quality stereo image reconstruction. The network predicts the amount of error in the lower quality reconstruction with respect to the high-quality one, having only view the former through its input. We evaluate our approach by correcting two-dimensional (2D) inverse-depth images extracted from the 3D model, and show that our method improves the quality of these depth reconstructions by up to a relative 10% RMSE.
Tasks	Image Reconstruction
Published	2018-01-27
URL	http://arxiv.org/abs/1801.09128v1
PDF	http://arxiv.org/pdf/1801.09128v1.pdf
PWC	https://paperswithcode.com/paper/meshed-up-learnt-error-correction-in-3d
Repo
Framework

Prioritizing Starting States for Reinforcement Learning


Title	Prioritizing Starting States for Reinforcement Learning
Authors	Arash Tavakoli, Vitaly Levdik, Riashat Islam, Petar Kormushev
Abstract	Online, off-policy reinforcement learning algorithms are able to use an experience memory to remember and replay past experiences. In prior work, this approach was used to stabilize training by breaking the temporal correlations of the updates and avoiding the rapid forgetting of possibly rare experiences. In this work, we propose a conceptually simple framework that uses an experience memory to help exploration by prioritizing the starting states from which the agent starts acting in the environment, importantly, in a fashion that is also compatible with on-policy algorithms. Given the capacity to restart the agent in states corresponding to its past observations, we achieve this objective by (i) enabling the agent to restart in states belonging to significant past experiences (e.g., nearby goals), and (ii) promoting faster coverage of the state space through starting from a more diverse set of states. While, using a good priority measure to identify significant past transitions, we expect case (i) to more considerably help exploration in certain domains (e.g., sparse reward tasks), we hypothesize that case (ii) will generally be beneficial, even without any prioritization. We show empirically that our approach improves learning performance for both off-policy and on-policy deep reinforcement learning methods, with most notable gains in highly sparse reward tasks.
Tasks
Published	2018-11-27
URL	http://arxiv.org/abs/1811.11298v2
PDF	http://arxiv.org/pdf/1811.11298v2.pdf
PWC	https://paperswithcode.com/paper/prioritizing-starting-states-for
Repo
Framework