October 17, 2019

2891 words 14 mins read

Paper Group ANR 706

Stability-certified reinforcement learning: A control-theoretic perspective. Distributed Stochastic Multi-Task Learning with Graph Regularization. A Comparative Analysis of Registration Tools: Traditional vs Deep Learning Approach on High Resolution Tissue Cleared Data. A Probe Towards Understanding GAN and VAE Models. Novel Convolution Kernels for …

Stability-certified reinforcement learning: A control-theoretic perspective


Title	Stability-certified reinforcement learning: A control-theoretic perspective
Authors	Ming Jin, Javad Lavaei
Abstract	We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing controllers by exploiting problem-specific structures; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two decentralized control tasks, namely multi-flight formation and power system frequency regulation, demonstrate that the reinforcement learning agents can have high performance within the stability-certified parameter space, and also exhibit stable learning behaviors in the long run.
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11505v1
PDF	http://arxiv.org/pdf/1810.11505v1.pdf
PWC	https://paperswithcode.com/paper/stability-certified-reinforcement-learning-a
Repo
Framework

Distributed Stochastic Multi-Task Learning with Graph Regularization


Title	Distributed Stochastic Multi-Task Learning with Graph Regularization
Authors	Weiran Wang, Jialei Wang, Mladen Kolar, Nathan Srebro
Abstract	We propose methods for distributed graph-based multi-task learning that are based on weighted averaging of messages from other machines. Uniform averaging or diminishing stepsize in these methods would yield consensus (single task) learning. We show how simply skewing the averaging weights or controlling the stepsize allows learning different, but related, tasks on the different machines.
Tasks	Multi-Task Learning
Published	2018-02-11
URL	http://arxiv.org/abs/1802.03830v1
PDF	http://arxiv.org/pdf/1802.03830v1.pdf
PWC	https://paperswithcode.com/paper/distributed-stochastic-multi-task-learning
Repo
Framework

A Comparative Analysis of Registration Tools: Traditional vs Deep Learning Approach on High Resolution Tissue Cleared Data


Title	A Comparative Analysis of Registration Tools: Traditional vs Deep Learning Approach on High Resolution Tissue Cleared Data
Authors	Abdullah Nazib, Clinton Fookes, Dimitri Perrin
Abstract	Image registration plays an important role in comparing images. It is particularly important in analyzing medical images like CT, MRI, PET, etc. to quantify different biological samples, to monitor disease progression and to fuse different modalities to support better diagnosis. The recent emergence of tissue clearing protocols enable us to take images at cellular level resolution. Image registration tools developed for other modalities are currently unable to manage images of such extreme high resolution. The recent popularity of deep learning based methods in the computer vision community justifies a rigorous investigation of deep-learning based methods on tissue cleared images along with their traditional counterparts. In this paper, we investigate and compare the performance of a deep learning based registration method with traditional optimization based methods on samples from tissue-clearing methods. From the comparative results it is found that a deep-learning based method outperforms all traditional registration tools in terms of registration time and has achieved promising registration accuracy.
Tasks	Image Registration
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08315v1
PDF	http://arxiv.org/pdf/1810.08315v1.pdf
PWC	https://paperswithcode.com/paper/a-comparative-analysis-of-registration-tools
Repo
Framework

A Probe Towards Understanding GAN and VAE Models


Title	A Probe Towards Understanding GAN and VAE Models
Authors	Lu Mi, Macheng Shen, Jingzhao Zhang
Abstract	This project report compares some known GAN and VAE models proposed prior to 2017. There has been significant progress after we finished this report. We upload this report as an introduction to generative models and provide some personal interpretations supported by empirical evidence. Both generative adversarial network models and variational autoencoders have been widely used to approximate probability distributions of data sets. Although they both use parametrized distributions to approximate the underlying data distribution, whose exact inference is intractable, their behaviors are very different. We summarize our experiment results that compare these two categories of models in terms of fidelity and mode collapse. We provide a hypothesis to explain their different behaviors and propose a new model based on this hypothesis. We further tested our proposed model on MNIST dataset and CelebA dataset.
Tasks
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05676v2
PDF	http://arxiv.org/pdf/1812.05676v2.pdf
PWC	https://paperswithcode.com/paper/a-probe-towards-understanding-gan-and-vae
Repo
Framework

Novel Convolution Kernels for Computer Vision and Shape Analysis based on Electromagnetism


Title	Novel Convolution Kernels for Computer Vision and Shape Analysis based on Electromagnetism
Authors	Dominique Beaini, Sofiane Achiche, Yann-Seing Law-Kam Cio, Maxime Raison
Abstract	Computer vision is a growing field with a lot of new applications in automation and robotics, since it allows the analysis of images and shapes for the generation of numerical or analytical information. One of the most used method of information extraction is image filtering through convolution kernels, with each kernel specialized for specific applications. The objective of this paper is to present a novel convolution kernels, based on principles of electromagnetic potentials and fields, for a general use in computer vision and to demonstrate its usage for shape and stroke analysis. Such filtering possesses unique geometrical properties that can be interpreted using well understood physics theorems. Therefore, this paper focuses on the development of the electromagnetic kernels and on their application on images for shape and stroke analysis. It also presents several interesting features of electromagnetic kernels, such as resolution, size and orientation independence, robustness to noise and deformation, long distance stroke interaction and ability to work with 3D images
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07996v1
PDF	http://arxiv.org/pdf/1806.07996v1.pdf
PWC	https://paperswithcode.com/paper/novel-convolution-kernels-for-computer-vision
Repo
Framework

Novelty Detection with GAN


Title	Novelty Detection with GAN
Authors	Mark Kliger, Shachar Fleishman
Abstract	The ability of a classifier to recognize unknown inputs is important for many classification-based systems. We discuss the problem of simultaneous classification and novelty detection, i.e. determining whether an input is from the known set of classes and from which specific class, or from an unknown domain and does not belong to any of the known classes. We propose a method based on the Generative Adversarial Networks (GAN) framework. We show that a multi-class discriminator trained with a generator that generates samples from a mixture of nominal and novel data distributions is the optimal novelty detector. We approximate that generator with a mixture generator trained with the Feature Matching loss and empirically show that the proposed method outperforms conventional methods for novelty detection. Our findings demonstrate a simple, yet powerful new application of the GAN framework for the task of novelty detection.
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10560v1
PDF	http://arxiv.org/pdf/1802.10560v1.pdf
PWC	https://paperswithcode.com/paper/novelty-detection-with-gan
Repo
Framework

Graph Laplacian Regularized Graph Convolutional Networks for Semi-supervised Learning


Title	Graph Laplacian Regularized Graph Convolutional Networks for Semi-supervised Learning
Authors	Bo Jiang, Doudou Lin
Abstract	Recently, graph convolutional network (GCN) has been widely used for semi-supervised classification and deep feature representation on graph-structured data. However, existing GCN generally fails to consider the local invariance constraint in learning and representation process. That is, if two data points Xi and Xj are close in the intrinsic geometry of the data distribution, then their labels/representations should also be close to each other. This is known as local invariance assumption which plays an essential role in the development of various kinds of traditional algorithms, such as dimensionality reduction and semi-supervised learning, in machine learning area. To overcome this limitation, we introduce a graph Laplacian GCN (gLGCN) approach for graph data representation and semi-supervised classification. The proposed gLGCN model is capable of encoding both graph structure and node features together while maintains the local invariance constraint naturally for robust data representation and semi-supervised classification. Experiments show the benefit of the benefits the proposed gLGCN network.
Tasks	Dimensionality Reduction
Published	2018-09-26
URL	http://arxiv.org/abs/1809.09839v1
PDF	http://arxiv.org/pdf/1809.09839v1.pdf
PWC	https://paperswithcode.com/paper/graph-laplacian-regularized-graph
Repo
Framework

Question Generation from SQL Queries Improves Neural Semantic Parsing


Title	Question Generation from SQL Queries Improves Neural Semantic Parsing
Authors	Daya Guo, Yibo Sun, Duyu Tang, Nan Duan, Jian Yin, Hong Chi, James Cao, Peng Chen, Ming Zhou
Abstract	We study how to learn a semantic parser of state-of-the-art accuracy with less supervised training data. We conduct our study on WikiSQL, the largest hand-annotated semantic parsing dataset to date. First, we demonstrate that question generation is an effective method that empowers us to learn a state-of-the-art neural network based semantic parser with thirty percent of the supervised training data. Second, we show that applying question generation to the full supervised training data further improves the state-of-the-art model. In addition, we observe that there is a logarithmic relationship between the accuracy of a semantic parser and the amount of training data.
Tasks	Question Generation, Semantic Parsing
Published	2018-08-20
URL	http://arxiv.org/abs/1808.06304v2
PDF	http://arxiv.org/pdf/1808.06304v2.pdf
PWC	https://paperswithcode.com/paper/question-generation-from-sql-queries-improves
Repo
Framework

Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension


Title	Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
Authors	Rajarshi Das, Tsendsuren Munkhdalai, Xingdi Yuan, Adam Trischler, Andrew McCallum
Abstract	We propose a neural machine-reading model that constructs dynamic knowledge graphs from procedural text. It builds these graphs recurrently for each step of the described procedure, and uses them to track the evolving states of participant entities. We harness and extend a recently proposed machine reading comprehension (MRC) model to query for entity states, since these states are generally communicated in spans of text and MRC models perform well in extracting entity-centric spans. The explicit, structured, and evolving knowledge graph representations that our model constructs can be used in downstream question answering tasks to improve machine comprehension of text, as we demonstrate empirically. On two comprehension tasks from the recently proposed PROPARA dataset (Dalvi et al., 2018), our model achieves state-of-the-art results. We further show that our model is competitive on the RECIPES dataset (Kiddon et al., 2015), suggesting it may be generally applicable. We present some evidence that the model’s knowledge graphs help it to impose commonsense constraints on its predictions.
Tasks	Knowledge Graphs, Machine Reading Comprehension, Question Answering, Reading Comprehension
Published	2018-10-12
URL	http://arxiv.org/abs/1810.05682v1
PDF	http://arxiv.org/pdf/1810.05682v1.pdf
PWC	https://paperswithcode.com/paper/building-dynamic-knowledge-graphs-from-text
Repo
Framework

Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM


Title	Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM
Authors	German Abrevaya, Irina Rish, Aleksandr Y. Aravkin, Guillermo Cecchi, James Kozloski, Pablo Polosecki, Peng Zheng, Silvina Ponce Dawson, Juliana Rhee, David Cox
Abstract	Many real-world data sets, especially in biology, are produced by complex nonlinear dynamical systems. In this paper, we focus on brain calcium imaging (CaI) of different organisms (zebrafish and rat), aiming to build a model of joint activation dynamics in large neuronal populations, including the whole brain of zebrafish. We propose a new approach for capturing dynamics of temporal SVD components that uses the coupled (multivariate) van der Pol (VDP) oscillator, a nonlinear ordinary differential equation (ODE) model describing neural activity, with a new parameter estimation technique that combines variable projection optimization and stochastic search. We show that the approach successfully handles nonlinearities and hidden state variables in the coupled VDP. The approach is accurate, achieving 0.82 to 0.94 correlation between the actual and model-generated components, and interpretable, as VDP’s coupling matrix reveals anatomically meaningful positive (excitatory) and negative (inhibitory) interactions across different brain subsystems corresponding to spatial SVD components. Moreover, VDP is comparable to (or sometimes better than) recurrent neural networks (LSTM) for (short-term) prediction of future brain activity; VDP needs less parameters to train, which was a plus on our small training data. Finally, the overall best predictive method, greatly outperforming both VDP and LSTM in short- and long-term predictive settings on both datasets, was the new hybrid VDP-LSTM approach that used VDP to simulate large domain-specific dataset for LSTM pretraining; note that simple LSTM data-augmentation via noisy versions of training data was much less effective.
Tasks	Data Augmentation, Time Series
Published	2018-05-24
URL	https://arxiv.org/abs/1805.09874v2
PDF	https://arxiv.org/pdf/1805.09874v2.pdf
PWC	https://paperswithcode.com/paper/learning-nonlinear-brain-dynamics-van-der-pol
Repo
Framework

Task adapted reconstruction for inverse problems


Title	Task adapted reconstruction for inverse problems
Authors	Jonas Adler, Sebastian Lunz, Olivier Verdier, Carola-Bibiane Schönlieb, Ozan Öktem
Abstract	The paper considers the problem of performing a task defined on a model parameter that is only observed indirectly through noisy data in an ill-posed inverse problem. A key aspect is to formalize the steps of reconstruction and task as appropriate estimators (non-randomized decision rules) in statistical estimation problems. The implementation makes use of (deep) neural networks to provide a differentiable parametrization of the family of estimators for both steps. These networks are combined and jointly trained against suitable supervised training data in order to minimize a joint differentiable loss function, resulting in an end-to-end task adapted reconstruction method. The suggested framework is generic, yet adaptable, with a plug-and-play structure for adjusting both the inverse problem and the task at hand. More precisely, the data model (forward operator and statistical model of the noise) associated with the inverse problem is exchangeable, e.g., by using neural network architecture given by a learned iterative method. Furthermore, any task that is encodable as a trainable neural network can be used. The approach is demonstrated on joint tomographic image reconstruction, classification and joint tomographic image reconstruction segmentation.
Tasks	Image Reconstruction
Published	2018-08-27
URL	http://arxiv.org/abs/1809.00948v1
PDF	http://arxiv.org/pdf/1809.00948v1.pdf
PWC	https://paperswithcode.com/paper/task-adapted-reconstruction-for-inverse
Repo
Framework

A Novel Disparity Transformation Algorithm for Road Segmentation


Title	A Novel Disparity Transformation Algorithm for Road Segmentation
Authors	Rui Fan, Mohammud Junaid Bocus, Naim Dahnoun
Abstract	The disparity information provided by stereo cameras has enabled advanced driver assistance systems to estimate road area more accurately and effectively. In this paper, a novel disparity transformation algorithm is proposed to extract road areas from dense disparity maps by making the disparity value of the road pixels become similar. The transformation is achieved using two parameters: roll angle and fitted disparity value with respect to each row. To achieve a better processing efficiency, golden section search and dynamic programming are utilised to estimate the roll angle and the fitted disparity value, respectively. By performing a rotation around the estimated roll angle, the disparity distribution of each row becomes very compact. This further improves the accuracy of the road model estimation, as demonstrated by the various experimental results in this paper. Finally, the Otsu’s thresholding method is applied to the transformed disparity map and the roads can be accurately segmented at pixel level.
Tasks
Published	2018-08-08
URL	http://arxiv.org/abs/1808.02837v1
PDF	http://arxiv.org/pdf/1808.02837v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-disparity-transformation-algorithm
Repo
Framework

Acoustic feature learning using cross-domain articulatory measurements


Title	Acoustic feature learning using cross-domain articulatory measurements
Authors	Qingming Tang, Weiran Wang, Karen Livescu
Abstract	Previous work has shown that it is possible to improve speech recognition by learning acoustic features from paired acoustic-articulatory data, for example by using canonical correlation analysis (CCA) or its deep extensions. One limitation of this prior work is that the learned feature models are difficult to port to new datasets or domains, and articulatory data is not available for most speech corpora. In this work we study the problem of acoustic feature learning in the setting where we have access to an external, domain-mismatched dataset of paired speech and articulatory measurements, either with or without labels. We develop methods for acoustic feature learning in these settings, based on deep variational CCA and extensions that use both source and target domain data and labels. Using this approach, we improve phonetic recognition accuracies on both TIMIT and Wall Street Journal and analyze a number of design choices.
Tasks	Speech Recognition
Published	2018-03-19
URL	http://arxiv.org/abs/1803.06805v2
PDF	http://arxiv.org/pdf/1803.06805v2.pdf
PWC	https://paperswithcode.com/paper/acoustic-feature-learning-using-cross-domain
Repo
Framework

S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction


Title	S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction
Authors	Bolun Zheng, Rui Sun, Xiang Tian, Yaowu Chen
Abstract	Recent studies have used deep residual convolutional neural networks (CNNs) for JPEG compression artifact reduction. This study proposes a scalable CNN called S-Net. Our approach effectively adjusts the network scale dynamically in a multitask system for real-time operation with little performance loss. It offers a simple and direct technique to evaluate the performance gains obtained with increasing network depth, and it is helpful for removing redundant network layers to maximize the network efficiency. We implement our architecture using the Keras framework with the TensorFlow backend on an NVIDIA K80 GPU server. We train our models on the DIV2K dataset and evaluate their performance on public benchmark datasets. To validate the generality and universality of the proposed method, we created and utilized a new dataset, called WIN143, for over-processed images evaluation. Experimental results indicate that our proposed approach outperforms other CNN-based methods and achieves state-of-the-art performance.
Tasks	Jpeg Compression Artifact Reduction
Published	2018-10-18
URL	http://arxiv.org/abs/1810.07960v1
PDF	http://arxiv.org/pdf/1810.07960v1.pdf
PWC	https://paperswithcode.com/paper/s-net-a-scalable-convolutional-neural-network
Repo
Framework

Deep Neural Ranking for Crowdsourced Geopolitical Event Forecasting


Title	Deep Neural Ranking for Crowdsourced Geopolitical Event Forecasting
Authors	Giuseppe Nebbione, Derek Doran, Srikanth Nadella, Brandon Minnery
Abstract	There are many examples of ‘wisdom of the crowd’ effects in which the large number of participants imparts confidence in the collective judgment of the crowd. But how do we form an aggregated judgment when the size of the crowd is limited? Whose judgments do we include, and whose do we accord the most weight? This paper considers this problem in the context of geopolitical event forecasting, where volunteer analysts are queried to give their expertise, confidence, and predictions about the outcome of an event. We develop a forecast aggregation model that integrates topical information about a question, meta-data about a pair of forecasters, and their predictions in a deep siamese neural network that decides which forecasters’ predictions are more likely to be close to the correct response. A ranking of the forecasters is induced from a tournament of pair-wise forecaster comparisons, with the ranking used to create an aggregate forecast. Preliminary results find the aggregate prediction of the best forecasters ranked by our deep siamese network model consistently beats typical aggregation techniques by Brier score.
Tasks
Published	2018-10-23
URL	http://arxiv.org/abs/1810.09620v1
PDF	http://arxiv.org/pdf/1810.09620v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-ranking-for-crowdsourced
Repo
Framework