October 19, 2019

3143 words 15 mins read

Paper Group ANR 276

Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces. Overhead Detection: Beyond 8-bits and RGB. Counterfactual Mean Embeddings. Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze. Dependency-based Hybrid Trees for Semantic Parsing. Distinct patterns of syntactic a …

Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces


Title	Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces
Authors	Motoya Ohnishi, Masahiro Yukawa, Mikael Johansson, Masashi Sugiyama
Abstract	Motivated by the success of reinforcement learning (RL) for discrete-time tasks such as AlphaGo and Atari games, there has been a recent surge of interest in using RL for continuous-time control of physical systems (cf. many challenging tasks in OpenAI Gym and DeepMind Control Suite). Since discretization of time is susceptible to error, it is methodologically more desirable to handle the system dynamics directly in continuous time. However, very few techniques exist for continuous-time RL and they lack flexibility in value function approximation. In this paper, we propose a novel framework for model-based continuous-time value function approximation in reproducing kernel Hilbert spaces. The resulting framework is so flexible that it can accommodate any kind of kernel-based approach, such as Gaussian processes and kernel adaptive filters, and it allows us to handle uncertainties and nonstationarity without prior knowledge about the environment or what basis functions to employ. We demonstrate the validity of the presented framework through experiments.
Tasks	Atari Games, Gaussian Processes
Published	2018-06-08
URL	http://arxiv.org/abs/1806.02985v3
PDF	http://arxiv.org/pdf/1806.02985v3.pdf
PWC	https://paperswithcode.com/paper/continuous-time-value-function-approximation
Repo
Framework

Overhead Detection: Beyond 8-bits and RGB


Title	Overhead Detection: Beyond 8-bits and RGB
Authors	Eliza Mace, Keith Manville, Monica Barbu-McInnis, Michael Laielli, Matthew Klaric, Samuel Dooley
Abstract	This study uses the challenging and publicly available SpaceNet dataset to establish a performance baseline for a state-of-the-art object detector in satellite imagery. Specifically, we examine how various features of the data affect building detection accuracy with respect to the Intersection over Union metric. We demonstrate that the performance of the R-FCN detection algorithm on imagery with a 1.5 meter ground sample distance and three spectral bands increases by over 32% by using 13-bit data, as opposed to 8-bit data at the same spatial and spectral resolution. We also establish accuracy trends with respect to building size and scene density. Finally, we propose and evaluate multiple methods for integrating additional spectral information into off-the-shelf deep learning architectures. Interestingly, our methods are robust to the choice of spectral bands and we note no significant performance improvement when adding additional bands.
Tasks
Published	2018-08-07
URL	http://arxiv.org/abs/1808.02443v1
PDF	http://arxiv.org/pdf/1808.02443v1.pdf
PWC	https://paperswithcode.com/paper/overhead-detection-beyond-8-bits-and-rgb
Repo
Framework

Counterfactual Mean Embeddings


Title	Counterfactual Mean Embeddings
Authors	Krikamol Muandet, Motonobu Kanagawa, Sorawit Saengkyongam, Sanparith Marukatat
Abstract	Counterfactual inference has become a ubiquitous tool in online advertisement, recommendation systems, medical diagnosis, and finance. Accurate modeling of outcome distributions associated with different interventions—known as counterfactual distributions—is crucial for the success of these applications. In this work, we propose to model counterfactual distributions using a novel Hilbert space representation called counterfactual mean embedding (CME). The CME embeds the associated counterfactual distribution into a reproducing kernel Hilbert space (RKHS) endowed with a positive definite kernel, which allows us to perform causal inference over the entire landscape of the counterfactual distribution. Based on this representation, we propose a distributional treatment effect (DTE) which can quantify the causal effect over entire outcome distributions. Our approach is nonparametric as the CME can be estimated consistently from observational data without requiring any parametric assumption about the underlying distributions. We also establish a rate of convergence of the proposed estimator which depends on the smoothness of the conditional mean and the Radon-Nikodym derivative of the underlying marginal distributions. Furthermore, our framework also allows for more complex outcomes such as images, sequences, and graphs. Lastly, our experimental results on synthetic data and off-policy evaluation tasks demonstrate the advantages of the proposed estimator.
Tasks	Causal Inference, Counterfactual Inference, Medical Diagnosis, Recommendation Systems
Published	2018-05-22
URL	https://arxiv.org/abs/1805.08845v2
PDF	https://arxiv.org/pdf/1805.08845v2.pdf
PWC	https://paperswithcode.com/paper/counterfactual-mean-embedding-a-kernel-method
Repo
Framework

Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze


Title	Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze
Authors	Diego Romeres, Devesh Jha, Alberto Dalla Libera, William Yerazunis, Daniel Nikovski
Abstract	This paper presents a problem of model learning for the purpose of learning how to navigate a ball to a goal state in a circular maze environment with two degrees of freedom. The motion of the ball in the maze environment is influenced by several non-linear effects such as dry friction and contacts, which are difficult to model physically. We propose a semiparametric model to estimate the motion dynamics of the ball based on Gaussian Process Regression equipped with basis functions obtained from physics first principles. The accuracy of this semiparametric model is shown not only in estimation but also in prediction at n-steps ahead and its compared with standard algorithms for model learning. The learned model is then used in a trajectory optimization algorithm to compute ball trajectories. We propose the system presented in the paper as a benchmark problem for reinforcement and robot learning, for its interesting and challenging dynamics and its relative ease of reproducibility.
Tasks	Gaussian Processes
Published	2018-09-13
URL	http://arxiv.org/abs/1809.04993v2
PDF	http://arxiv.org/pdf/1809.04993v2.pdf
PWC	https://paperswithcode.com/paper/semiparametrical-gaussian-processes-learning
Repo
Framework

Dependency-based Hybrid Trees for Semantic Parsing


Title	Dependency-based Hybrid Trees for Semantic Parsing
Authors	Zhanming Jie, Wei Lu
Abstract	We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the semantic information is interpreted as the latent dependency between the natural language words in our joint representation. Such dependency information can capture the interactions between the semantics and natural language words. We integrate a neural component into our model and propose an efficient dynamic-programming algorithm to perform tractable inference. Through extensive experiments on the standard multilingual GeoQuery dataset with eight languages, we demonstrate that our proposed approach is able to achieve state-of-the-art performance across several languages. Analysis also justifies the effectiveness of using our new dependency-based representation.
Tasks	Semantic Parsing
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00107v1
PDF	http://arxiv.org/pdf/1809.00107v1.pdf
PWC	https://paperswithcode.com/paper/dependency-based-hybrid-trees-for-semantic
Repo
Framework

Distinct patterns of syntactic agreement errors in recurrent networks and humans


Title	Distinct patterns of syntactic agreement errors in recurrent networks and humans
Authors	Tal Linzen, Brian Leonard
Abstract	Determining the correct form of a verb in context requires an understanding of the syntactic structure of the sentence. Recurrent neural networks have been shown to perform this task with an error rate comparable to humans, despite the fact that they are not designed with explicit syntactic representations. To examine the extent to which the syntactic representations of these networks are similar to those used by humans when processing sentences, we compare the detailed pattern of errors that RNNs and humans make on this task. Despite significant similarities (attraction errors, asymmetry between singular and plural subjects), the error patterns differed in important ways. In particular, in complex sentences with relative clauses error rates increased in RNNs but decreased in humans. Furthermore, RNNs showed a cumulative effect of attractors but humans did not. We conclude that at least in some respects the syntactic representations acquired by RNNs are fundamentally different from those used by humans.
Tasks
Published	2018-07-18
URL	http://arxiv.org/abs/1807.06882v1
PDF	http://arxiv.org/pdf/1807.06882v1.pdf
PWC	https://paperswithcode.com/paper/distinct-patterns-of-syntactic-agreement
Repo
Framework

Multi-Reward Reinforced Summarization with Saliency and Entailment


Title	Multi-Reward Reinforced Summarization with Saliency and Entailment
Authors	Ramakanth Pasunuru, Mohit Bansal
Abstract	Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and non-redundancy. In this work, we address these three important aspects of a good summary via a reinforcement learning approach with two novel reward functions: ROUGESal and Entail, on top of a coverage-based baseline. The ROUGESal reward modifies the ROUGE metric by up-weighting the salient phrases/words detected via a keyphrase classifier. The Entail reward gives high (length-normalized) scores to logically-entailed summaries using an entailment classifier. Further, we show superior performance improvement when these rewards are combined with traditional metric (ROUGE) based rewards, via our novel and effective multi-reward approach of optimizing multiple rewards simultaneously in alternate mini-batches. Our method achieves the new state-of-the-art results (including human evaluation) on the CNN/Daily Mail dataset as well as strong improvements in a test-only transfer setup on DUC-2002.
Tasks	Abstractive Text Summarization, Text Summarization
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06451v2
PDF	http://arxiv.org/pdf/1804.06451v2.pdf
PWC	https://paperswithcode.com/paper/multi-reward-reinforced-summarization-with
Repo
Framework

Auto-ML Deep Learning for Rashi Scripts OCR


Title	Auto-ML Deep Learning for Rashi Scripts OCR
Authors	Shahar Mahpod, Yosi Keller
Abstract	In this work we propose an OCR scheme for manuscripts printed in Rashi font that is an ancient Hebrew font and corresponding dialect used in religious Jewish literature, for more than 600 years. The proposed scheme utilizes a convolution neural network (CNN) for visual inference and Long-Short Term Memory (LSTM) to learn the Rashi scripts dialect. In particular, we derive an AutoML scheme to optimize the CNN architecture, and a book-specific CNN training to improve the OCR accuracy. The proposed scheme achieved an accuracy of more than 99.8% using a dataset of more than 3M annotated letters from the Responsa Project dataset.
Tasks	AutoML, Optical Character Recognition
Published	2018-11-03
URL	https://arxiv.org/abs/1811.01290v2
PDF	https://arxiv.org/pdf/1811.01290v2.pdf
PWC	https://paperswithcode.com/paper/auto-ml-deep-learning-for-rashi-scripts-ocr
Repo
Framework

Natural Language Processing for Information Extraction


Title	Natural Language Processing for Information Extraction
Authors	Sonit Singh
Abstract	With rise of digital age, there is an explosion of information in the form of news, articles, social media, and so on. Much of this data lies in unstructured form and manually managing and effectively making use of it is tedious, boring and labor intensive. This explosion of information and need for more sophisticated and efficient information handling tools gives rise to Information Extraction(IE) and Information Retrieval(IR) technology. Information Extraction systems takes natural language text as input and produces structured information specified by certain criteria, that is relevant to a particular application. Various sub-tasks of IE such as Named Entity Recognition, Coreference Resolution, Named Entity Linking, Relation Extraction, Knowledge Base reasoning forms the building blocks of various high end Natural Language Processing (NLP) tasks such as Machine Translation, Question-Answering System, Natural Language Understanding, Text Summarization and Digital Assistants like Siri, Cortana and Google Now. This paper introduces Information Extraction technology, its various sub-tasks, highlights state-of-the-art research in various IE subtasks, current challenges and future research directions.
Tasks	Coreference Resolution, Entity Linking, Information Retrieval, Machine Translation, Named Entity Recognition, Question Answering, Relation Extraction, Text Summarization
Published	2018-07-06
URL	http://arxiv.org/abs/1807.02383v1
PDF	http://arxiv.org/pdf/1807.02383v1.pdf
PWC	https://paperswithcode.com/paper/natural-language-processing-for-information
Repo
Framework

Deep Learning based Estimation of Weaving Target Maneuvers


Title	Deep Learning based Estimation of Weaving Target Maneuvers
Authors	Vitaly Shalumov, Itzik Klein
Abstract	In target tracking, the estimation of an unknown weaving target frequency is crucial for improving the miss distance. The estimation process is commonly carried out in a Kalman framework. The objective of this paper is to examine the potential of using neural networks in target tracking applications. To that end, we propose estimating the weaving frequency using deep neural networks, instead of classical Kalman framework based estimation. Particularly, we focus on the case where a set of possible constant target frequencies is known. Several neural network architectures, requiring low computational resources were designed to estimate the unknown frequency out of the known set of frequencies. The proposed approach performance is compared with the multiple model adaptive estimation algorithm. Simulation results show that in the examined scenarios, deep neural network outperforms multiple model adaptive estimation in terms of accuracy and the amount of required measurements to convergence.
Tasks
Published	2018-06-13
URL	http://arxiv.org/abs/1806.06913v1
PDF	http://arxiv.org/pdf/1806.06913v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-estimation-of-weaving
Repo
Framework

Topic Memory Networks for Short Text Classification


Title	Topic Memory Networks for Short Text Classification
Authors	Jichuan Zeng, Jing Li, Yan Song, Cuiyun Gao, Michael R. Lyu, Irwin King
Abstract	Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on short text classification, meanwhile generates coherent topics.
Tasks	Text Classification
Published	2018-09-11
URL	http://arxiv.org/abs/1809.03664v1
PDF	http://arxiv.org/pdf/1809.03664v1.pdf
PWC	https://paperswithcode.com/paper/topic-memory-networks-for-short-text
Repo
Framework

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds


Title	Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds
Authors	Francis Engelmann, Theodora Kontogianni, Alexander Hermans, Bastian Leibe
Abstract	Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate in the 2D image space. Direct semantic segmentation of unstructured 3D point clouds is still an open research problem. The recently proposed PointNet architecture presents an interesting step ahead in that it can operate on unstructured point clouds, achieving encouraging segmentation results. However, it subdivides the input points into a grid of blocks and processes each such block individually. In this paper, we investigate the question how such an architecture can be extended to incorporate larger-scale spatial context. We build upon PointNet and propose two extensions that enlarge the receptive field over the 3D scene. We evaluate the proposed strategies on challenging indoor and outdoor datasets and show improved results in both scenarios.
Tasks	3D Semantic Segmentation, Semantic Segmentation
Published	2018-02-05
URL	https://arxiv.org/abs/1802.01500v2
PDF	https://arxiv.org/pdf/1802.01500v2.pdf
PWC	https://paperswithcode.com/paper/exploring-spatial-context-for-3d-semantic
Repo
Framework

Towards a Definition of Disentangled Representations


Title	Towards a Definition of Disentangled Representations
Authors	Irina Higgins, David Amos, David Pfau, Sebastien Racaniere, Loic Matthey, Danilo Rezende, Alexander Lerchner
Abstract	How can intelligent agents solve a diverse set of tasks in a data-efficient manner? The disentangled representation learning approach posits that such an agent would benefit from separating out (disentangling) the underlying structure of the world into disjoint parts of its representation. However, there is no generally agreed-upon definition of disentangling, not least because it is unclear how to formalise the notion of world structure beyond toy datasets with a known ground truth generative process. Here we propose that a principled solution to characterising disentangled representations can be found by focusing on the transformation properties of the world. In particular, we suggest that those transformations that change only some properties of the underlying world state, while leaving all other properties invariant, are what gives exploitable structure to any kind of data. Similar ideas have already been successfully applied in physics, where the study of symmetry transformations has revolutionised the understanding of the world structure. By connecting symmetry transformations to vector representations using the formalism of group and representation theory we arrive at the first formal definition of disentangled representations. Our new definition is in agreement with many of the current intuitions about disentangling, while also providing principled resolutions to a number of previous points of contention. While this work focuses on formally defining disentangling - as opposed to solving the learning problem - we believe that the shift in perspective to studying data transformations can stimulate the development of better representation learning algorithms.
Tasks	Representation Learning
Published	2018-12-05
URL	http://arxiv.org/abs/1812.02230v1
PDF	http://arxiv.org/pdf/1812.02230v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-definition-of-disentangled
Repo
Framework

Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks


Title	Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks
Authors	Shuai Li
Abstract	We present a formal measure-theoretical theory of neural networks (NN) built on probability coupling theory. Our main contributions are summarized as follows. * Built on the formalism of probability coupling theory, we derive an algorithm framework, named Hierarchical Measure Group and Approximate System (HMGAS), nicknamed S-System, that is designed to learn the complex hierarchical, statistical dependency in the physical world. * We show that NNs are special cases of S-System when the probability kernels assume certain exponential family distributions. Activation Functions are derived formally. We further endow geometry on NNs through information geometry, show that intermediate feature spaces of NNs are stochastic manifolds, and prove that “distance” between samples is contracted as layers stack up. * S-System shows NNs are inherently stochastic, and under a set of realistic boundedness and diversity conditions, it enables us to prove that for large size nonlinear deep NNs with a class of losses, including the hinge loss, all local minima are global minima with zero loss errors, and regions around the minima are flat basins where all eigenvalues of Hessians are concentrated around zero, using tools and ideas from mean field theory, random matrix theory, and nonlinear operator equations. * S-System, the information-geometry structure and the optimization behaviors combined completes the analog between Renormalization Group (RG) and NNs. It shows that a NN is a complex adaptive system that estimates the statistic dependency of microscopic object, e.g., pixels, in multiple scales. Unlike clear-cut physical quantity produced by RG in physics, e.g., temperature, NNs renormalize/recompose manifolds emerging through learning/optimization that divide the sample space into highly semantically meaningful groups that are dictated by supervised labels (in supervised NNs).
Tasks
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12783v1
PDF	http://arxiv.org/pdf/1811.12783v1.pdf
PWC	https://paperswithcode.com/paper/measure-manifold-learning-and-optimization-a
Repo
Framework

Deep learning approach to Fourier ptychographic microscopy


Title	Deep learning approach to Fourier ptychographic microscopy
Authors	Thanh Nguyen, Yujia Xue, Yunzhe Li, Lei Tian, George Nehmetallah
Abstract	Convolutional neural networks (CNNs) have gained tremendous success in solving complex inverse problems. The aim of this work is to develop a novel CNN framework to reconstruct video sequence of dynamic live cells captured using a computational microscopy technique, Fourier ptychographic microscopy (FPM). The unique feature of the FPM is its capability to reconstruct images with both wide field-of-view (FOV) and high resolution, i.e. a large space-bandwidth-product (SBP), by taking a series of low resolution intensity images. For live cell imaging, a single FPM frame contains thousands of cell samples with different morphological features. Our idea is to fully exploit the statistical information provided by this large spatial ensemble so as to make predictions in a sequential measurement, without using any additional temporal dataset. Specifically, we show that it is possible to reconstruct high-SBP dynamic cell videos by a CNN trained only on the first FPM dataset captured at the beginning of a time-series experiment. Our CNN approach reconstructs a 12800X10800 pixels phase image using only ~25 seconds, a 50X speedup compared to the model-based FPM algorithm. In addition, the CNN further reduces the required number of images in each time frame by ~6X. Overall, this significantly improves the imaging throughput by reducing both the acquisition and computational times. The proposed CNN is based on the conditional generative adversarial network (cGAN) framework. Additionally, we also exploit transfer learning so that our pre-trained CNN can be further optimized to image other cell types. Our technique demonstrates a promising deep learning approach to continuously monitor large live-cell populations over an extended time and gather useful spatial and temporal information with sub-cellular resolution.
Tasks	Time Series, Transfer Learning
Published	2018-04-27
URL	http://arxiv.org/abs/1805.00334v3
PDF	http://arxiv.org/pdf/1805.00334v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-approach-to-fourier
Repo
Framework