July 27, 2019

3103 words 15 mins read

Paper Group ANR 712

Symbol, Conversational, and Societal Grounding with a Toy Robot. Effective Sequential Classifier Training for SVM-based Multitemporal Remote Sensing Image Classification. Simplified Stochastic Feedforward Neural Networks. Understanding GANs: the LQG Setting. Contractibility for Open Global Constraints. An investigation into machine learning approac …

Symbol, Conversational, and Societal Grounding with a Toy Robot


Title	Symbol, Conversational, and Societal Grounding with a Toy Robot
Authors	Casey Kennington, Sarah Plane
Abstract	Essential to meaningful interaction is grounding at the symbolic, conversational, and societal levels. We present ongoing work with Anki’s Cozmo toy robot as a research platform where we leverage the recent words-as-classifiers model of lexical semantics in interactive reference resolution tasks for language grounding.
Tasks
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10486v1
PDF	http://arxiv.org/pdf/1709.10486v1.pdf
PWC	https://paperswithcode.com/paper/symbol-conversational-and-societal-grounding
Repo
Framework

Effective Sequential Classifier Training for SVM-based Multitemporal Remote Sensing Image Classification


Title	Effective Sequential Classifier Training for SVM-based Multitemporal Remote Sensing Image Classification
Authors	Yiqing Guo, Xiuping Jia, David Paull
Abstract	The explosive availability of remote sensing images has challenged supervised classification algorithms such as Support Vector Machines (SVM), as training samples tend to be highly limited due to the expensive and laborious task of ground truthing. The temporal correlation and spectral similarity between multitemporal images have opened up an opportunity to alleviate this problem. In this study, a SVM-based Sequential Classifier Training (SCT-SVM) approach is proposed for multitemporal remote sensing image classification. The approach leverages the classifiers of previous images to reduce the required number of training samples for the classifier training of an incoming image. For each incoming image, a rough classifier is firstly predicted based on the temporal trend of a set of previous classifiers. The predicted classifier is then fine-tuned into a more accurate position with current training samples. This approach can be applied progressively to sequential image data, with only a small number of training samples being required from each image. Experiments were conducted with Sentinel-2A multitemporal data over an agricultural area in Australia. Results showed that the proposed SCT-SVM achieved better classification accuracies compared with two state-of-the-art model transfer algorithms. When training data are insufficient, the overall classification accuracy of the incoming image was improved from 76.18% to 94.02% with the proposed SCT-SVM, compared with those obtained without the assistance from previous images. These results demonstrate that the leverage of a priori information from previous images can provide advantageous assistance for later images in multitemporal image classification.
Tasks	Image Classification, Remote Sensing Image Classification
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04719v2
PDF	http://arxiv.org/pdf/1706.04719v2.pdf
PWC	https://paperswithcode.com/paper/effective-sequential-classifier-training-for
Repo
Framework

Simplified Stochastic Feedforward Neural Networks


Title	Simplified Stochastic Feedforward Neural Networks
Authors	Kimin Lee, Jaehyung Kim, Song Chong, Jinwoo Shin
Abstract	It has been believed that stochastic feedforward neural networks (SFNNs) have several advantages beyond deterministic deep neural networks (DNNs): they have more expressive power allowing multi-modal mappings and regularize better due to their stochastic nature. However, training large-scale SFNN is notoriously harder. In this paper, we aim at developing efficient training methods for SFNN, in particular using known architectures and pre-trained parameters of DNN. To this end, we propose a new intermediate stochastic model, called Simplified-SFNN, which can be built upon any baseline DNNand approximates certain SFNN by simplifying its upper latent units above stochastic ones. The main novelty of our approach is in establishing the connection between three models, i.e., DNN->Simplified-SFNN->SFNN, which naturally leads to an efficient training procedure of the stochastic models utilizing pre-trained parameters of DNN. Using several popular DNNs, we show how they can be effectively transferred to the corresponding stochastic models for both multi-modal and classification tasks on MNIST, TFD, CASIA, CIFAR-10, CIFAR-100 and SVHN datasets. In particular, we train a stochastic model of 28 layers and 36 million parameters, where training such a large-scale stochastic network is significantly challenging without using Simplified-SFNN
Tasks
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03188v1
PDF	http://arxiv.org/pdf/1704.03188v1.pdf
PWC	https://paperswithcode.com/paper/simplified-stochastic-feedforward-neural
Repo
Framework

Understanding GANs: the LQG Setting


Title	Understanding GANs: the LQG Setting
Authors	Soheil Feizi, Farzan Farnia, Tony Ginart, David Tse
Abstract	Generative Adversarial Networks (GANs) have become a popular method to learn a probability model from data. In this paper, we aim to provide an understanding of some of the basic issues surrounding GANs including their formulation, generalization and stability on a simple benchmark where the data has a high-dimensional Gaussian distribution. Even in this simple benchmark, the GAN problem has not been well-understood as we observe that existing state-of-the-art GAN architectures may fail to learn a proper generative distribution owing to (1) stability issues (i.e., convergence to bad local solutions or not converging at all), (2) approximation issues (i.e., having improper global GAN optimizers caused by inappropriate GAN’s loss functions), and (3) generalizability issues (i.e., requiring large number of samples for training). In this setup, we propose a GAN architecture which recovers the maximum-likelihood solution and demonstrates fast generalization. Moreover, we analyze global stability of different computational approaches for the proposed GAN optimization and highlight their pros and cons. Finally, we outline an extension of our model-based approach to design GANs in more complex setups than the considered Gaussian benchmark.
Tasks
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10793v2
PDF	http://arxiv.org/pdf/1710.10793v2.pdf
PWC	https://paperswithcode.com/paper/understanding-gans-the-lqg-setting
Repo
Framework

Contractibility for Open Global Constraints


Title	Contractibility for Open Global Constraints
Authors	Michael J. Maher
Abstract	Open forms of global constraints allow the addition of new variables to an argument during the execution of a constraint program. Such forms are needed for difficult constraint programming problems where problem construction and problem solving are interleaved, and fit naturally within constraint logic programming. However, in general, filtering that is sound for a global constraint can be unsound when the constraint is open. This paper provides a simple characterization, called contractibility, of the constraints where filtering remains sound when the constraint is open. With this characterization we can easily determine whether a constraint has this property or not. In the latter case, we can use it to derive a contractible approximation to the constraint. We demonstrate this work on both hard and soft constraints. In the process, we formulate two general classes of soft constraints.
Tasks
Published	2017-02-25
URL	http://arxiv.org/abs/1702.07889v1
PDF	http://arxiv.org/pdf/1702.07889v1.pdf
PWC	https://paperswithcode.com/paper/contractibility-for-open-global-constraints
Repo
Framework

An investigation into machine learning approaches for forecasting spatio-temporal demand in ride-hailing service


Title	An investigation into machine learning approaches for forecasting spatio-temporal demand in ride-hailing service
Authors	Ismaïl Saadi, Melvin Wong, Bilal Farooq, Jacques Teller, Mario Cools
Abstract	In this paper, we present machine learning approaches for characterizing and forecasting the short-term demand for on-demand ride-hailing services. We propose the spatio-temporal estimation of the demand that is a function of variable effects related to traffic, pricing and weather conditions. With respect to the methodology, a single decision tree, bootstrap-aggregated (bagged) decision trees, random forest, boosted decision trees, and artificial neural network for regression have been adapted and systematically compared using various statistics, e.g. R-square, Root Mean Square Error (RMSE), and slope. To better assess the quality of the models, they have been tested on a real case study using the data of DiDi Chuxing, the main on-demand ride hailing service provider in China. In the current study, 199,584 time-slots describing the spatio-temporal ride-hailing demand has been extracted with an aggregated-time interval of 10 mins. All the methods are trained and validated on the basis of two independent samples from this dataset. The results revealed that boosted decision trees provide the best prediction accuracy (RMSE=16.41), while avoiding the risk of over-fitting, followed by artificial neural network (20.09), random forest (23.50), bagged decision trees (24.29) and single decision tree (33.55).
Tasks
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02433v1
PDF	http://arxiv.org/pdf/1703.02433v1.pdf
PWC	https://paperswithcode.com/paper/an-investigation-into-machine-learning
Repo
Framework

A Batch-Incremental Video Background Estimation Model using Weighted Low-Rank Approximation of Matrices


Title	A Batch-Incremental Video Background Estimation Model using Weighted Low-Rank Approximation of Matrices
Authors	Aritra Dutta, Xin Li, Peter Richtárik
Abstract	Principal component pursuit (PCP) is a state-of-the-art approach for background estimation problems. Due to their higher computational cost, PCP algorithms, such as robust principal component analysis (RPCA) and its variants, are not feasible in processing high definition videos. To avoid the curse of dimensionality in those algorithms, several methods have been proposed to solve the background estimation problem in an incremental manner. We propose a batch-incremental background estimation model using a special weighted low-rank approximation of matrices. Through experiments with real and synthetic video sequences, we demonstrate that our method is superior to the state-of-the-art background estimation algorithms such as GRASTA, ReProCS, incPCP, and GFL.
Tasks
Published	2017-07-02
URL	http://arxiv.org/abs/1707.00281v1
PDF	http://arxiv.org/pdf/1707.00281v1.pdf
PWC	https://paperswithcode.com/paper/a-batch-incremental-video-background
Repo
Framework

Automatic Text Summarization Approaches to Speed up Topic Model Learning Process


Title	Automatic Text Summarization Approaches to Speed up Topic Model Learning Process
Authors	Mohamed Morchid, Juan-Manuel Torres-Moreno, Richard Dufour, Javier Ramírez-Rodríguez, Georges Linarès
Abstract	The number of documents available into Internet moves each day up. For this reason, processing this amount of information effectively and expressibly becomes a major concern for companies and scientists. Methods that represent a textual document by a topic representation are widely used in Information Retrieval (IR) to process big data such as Wikipedia articles. One of the main difficulty in using topic model on huge data collection is related to the material resources (CPU time and memory) required for model estimate. To deal with this issue, we propose to build topic spaces from summarized documents. In this paper, we present a study of topic space representation in the context of big data. The topic space representation behavior is analyzed on different languages. Experiments show that topic spaces estimated from text summaries are as relevant as those estimated from the complete documents. The real advantage of such an approach is the processing time gain: we showed that the processing time can be drastically reduced using summarized documents (more than 60% in general). This study finally points out the differences between thematic representations of documents depending on the targeted languages such as English or latin languages.
Tasks	Information Retrieval, Text Summarization
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06630v1
PDF	http://arxiv.org/pdf/1703.06630v1.pdf
PWC	https://paperswithcode.com/paper/automatic-text-summarization-approaches-to
Repo
Framework

Subset Labeled LDA for Large-Scale Multi-Label Classification


Title	Subset Labeled LDA for Large-Scale Multi-Label Classification
Authors	Yannis Papanikolaou, Grigorios Tsoumakas
Abstract	Labeled Latent Dirichlet Allocation (LLDA) is an extension of the standard unsupervised Latent Dirichlet Allocation (LDA) algorithm, to address multi-label learning tasks. Previous work has shown it to perform in par with other state-of-the-art multi-label methods. Nonetheless, with increasing label sets sizes LLDA encounters scalability issues. In this work, we introduce Subset LLDA, a simple variant of the standard LLDA algorithm, that not only can effectively scale up to problems with hundreds of thousands of labels but also improves over the LLDA state-of-the-art. We conduct extensive experiments on eight data sets, with label sets sizes ranging from hundreds to hundreds of thousands, comparing our proposed algorithm with the previously proposed LLDA algorithms (Prior–LDA, Dep–LDA), as well as the state of the art in extreme multi-label classification. The results show a steady advantage of our method over the other LLDA algorithms and competitive results compared to the extreme multi-label classification algorithms.
Tasks	Extreme Multi-Label Classification, Multi-Label Classification, Multi-Label Learning
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05480v1
PDF	http://arxiv.org/pdf/1709.05480v1.pdf
PWC	https://paperswithcode.com/paper/subset-labeled-lda-for-large-scale-multi
Repo
Framework

Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks


Title	Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks
Authors	Jun Liu, Gang Wang, Ling-Yu Duan, Kamila Abdiyeva, Alex C. Kot
Abstract	Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, Long Short-Term Memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies and dynamics in sequential data. As not all skeletal joints are informative for action recognition, and the irrelevant joints often bring noise which can degrade the performance, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In this paper, we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for skeleton based action recognition. This network is capable of selectively focusing on the informative joints in each frame of each skeleton sequence by using a global context memory cell. To further improve the attention capability of our network, we also introduce a recurrent attention mechanism, with which the attention performance of the network can be enhanced progressively. Moreover, we propose a stepwise training scheme in order to train our network effectively. Our approach achieves state-of-the-art performance on five challenging benchmark datasets for skeleton based action recognition.
Tasks	Skeleton Based Action Recognition, Temporal Action Localization
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05740v5
PDF	http://arxiv.org/pdf/1707.05740v5.pdf
PWC	https://paperswithcode.com/paper/skeleton-based-human-action-recognition-with
Repo
Framework

Formalized Lambek Calculus in Higher Order Logic (HOL4)


Title	Formalized Lambek Calculus in Higher Order Logic (HOL4)
Authors	Chun Tian
Abstract	In this project, a rather complete proof-theoretical formalization of Lambek Calculus (non-associative with arbitrary extensions) has been ported from Coq proof assistent to HOL4 theorem prover, with some improvements and new theorems. Three deduction systems (Syntactic Calculus, Natural Deduction and Sequent Calculus) of Lambek Calculus are defined with many related theorems proved. The equivalance between these systems are formally proved. Finally, a formalization of Sequent Calculus proofs (where Coq has built-in supports) has been designed and implemented in HOL4. Some basic results including the sub-formula properties of the so-called “cut-free” proofs are formally proved. This work can be considered as the preliminary work towards a language parser based on category grammars which is not multimodal but still has ability to support context-sensitive languages through customized extensions.
Tasks
Published	2017-05-20
URL	http://arxiv.org/abs/1705.07318v1
PDF	http://arxiv.org/pdf/1705.07318v1.pdf
PWC	https://paperswithcode.com/paper/formalized-lambek-calculus-in-higher-order
Repo
Framework

Adaptation and learning over networks for nonlinear system modeling


Title	Adaptation and learning over networks for nonlinear system modeling
Authors	Simone Scardapane, Jie Chen, Cédric Richard
Abstract	In this chapter, we analyze nonlinear filtering problems in distributed environments, e.g., sensor networks or peer-to-peer protocols. In these scenarios, the agents in the environment receive measurements in a streaming fashion, and they are required to estimate a common (nonlinear) model by alternating local computations and communications with their neighbors. We focus on the important distinction between single-task problems, where the underlying model is common to all agents, and multitask problems, where each agent might converge to a different model due to, e.g., spatial dependencies or other factors. Currently, most of the literature on distributed learning in the nonlinear case has focused on the single-task case, which may be a strong limitation in real-world scenarios. After introducing the problem and reviewing the existing approaches, we describe a simple kernel-based algorithm tailored for the multitask case. We evaluate the proposal on a simulated benchmark task, and we conclude by detailing currently open problems and lines of research.
Tasks
Published	2017-04-28
URL	http://arxiv.org/abs/1704.08913v1
PDF	http://arxiv.org/pdf/1704.08913v1.pdf
PWC	https://paperswithcode.com/paper/adaptation-and-learning-over-networks-for
Repo
Framework

Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling


Title	Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling
Authors	Xuefeng Xiao, Yafeng Yang, Tasweer Ahmad, Lianwen Jin, Tianhai Chang
Abstract	Currently, owing to the ubiquity of mobile devices, online handwritten Chinese character recognition (HCCR) has become one of the suitable choice for feeding input to cell phones and tablet devices. Over the past few years, larger and deeper convolutional neural networks (CNNs) have extensively been employed for improving character recognition performance. However, its substantial storage requirement is a significant obstacle in deploying such networks into portable electronic devices. To circumvent this problem, we propose a novel technique called DropWeight for pruning redundant connections in the CNN architecture. It is revealed that the proposed method not only treats streamlined architectures such as AlexNet and VGGNet well but also exhibits remarkable performance for deep residual network and inception network. We also demonstrate that global pooling is a better choice for building very compact online HCCR systems. Experiments were performed on the ICDAR-2013 online HCCR competition dataset using our proposed network, and it is found that the proposed approach requires only 0.57 MB for storage, whereas state-of-the-art CNN-based methods require up to 135 MB; meanwhile the performance is decreased only by 0.91%.
Tasks
Published	2017-05-15
URL	http://arxiv.org/abs/1705.05207v1
PDF	http://arxiv.org/pdf/1705.05207v1.pdf
PWC	https://paperswithcode.com/paper/design-of-a-very-compact-cnn-classifier-for
Repo
Framework

Monte-Carlo Tree Search by Best Arm Identification


Title	Monte-Carlo Tree Search by Best Arm Identification
Authors	Emilie Kaufmann, Wouter Koolen
Abstract	Recent advances in bandit tools and techniques for sequential learning are steadily enabling new applications and are promising the resolution of a range of challenging related problems. We study the game tree search problem, where the goal is to quickly identify the optimal move in a given game tree by sequentially sampling its stochastic payoffs. We develop new algorithms for trees of arbitrary depth, that operate by summarizing all deeper levels of the tree into confidence intervals at depth one, and applying a best arm identification procedure at the root. We prove new sample complexity guarantees with a refined dependence on the problem instance. We show experimentally that our algorithms outperform existing elimination-based algorithms and match previous special-purpose methods for depth-two trees.
Tasks
Published	2017-06-09
URL	http://arxiv.org/abs/1706.02986v2
PDF	http://arxiv.org/pdf/1706.02986v2.pdf
PWC	https://paperswithcode.com/paper/monte-carlo-tree-search-by-best-arm
Repo
Framework

Multi-Attribute Robust Component Analysis for Facial UV Maps


Title	Multi-Attribute Robust Component Analysis for Facial UV Maps
Authors	Stylianos Moschoglou, Evangelos Ververas, Yannis Panagakis, Mihalis Nicolaou, Stefanos Zafeiriou
Abstract	Recently, due to the collection of large scale 3D face models, as well as the advent of deep learning, a significant progress has been made in the field of 3D face alignment “in-the-wild”. That is, many methods have been proposed that establish sparse or dense 3D correspondences between a 2D facial image and a 3D face model. The utilization of 3D face alignment introduces new challenges and research directions, especially on the analysis of facial texture images. In particular, texture does not suffer any more from warping effects (that occurred when 2D face alignment methods were used). Nevertheless, since facial images are commonly captured in arbitrary recording conditions, a considerable amount of missing information and gross outliers is observed (e.g., due to self-occlusion, or subjects wearing eye-glasses). Given that many annotated databases have been developed for face analysis tasks, it is evident that component analysis techniques need to be developed in order to alleviate issues arising from the aforementioned challenges. In this paper, we propose a novel component analysis technique that is suitable for facial UV maps containing a considerable amount of missing information and outliers, while additionally, incorporates knowledge from various attributes (such as age and identity). We evaluate the proposed Multi-Attribute Robust Component Analysis (MA-RCA) on problems such as UV completion and age progression, where the proposed method outperforms compared techniques. Finally, we demonstrate that MA-RCA method is powerful enough to provide weak annotations for training deep learning systems for various applications, such as illumination transfer.
Tasks	Face Alignment
Published	2017-12-15
URL	http://arxiv.org/abs/1712.05799v1
PDF	http://arxiv.org/pdf/1712.05799v1.pdf
PWC	https://paperswithcode.com/paper/multi-attribute-robust-component-analysis-for
Repo
Framework