May 6, 2019

2921 words 14 mins read

Paper Group ANR 364

Information Processing by Nonlinear Phase Dynamics in Locally Connected Arrays. Robust Optimization for Tree-Structured Stochastic Network Design. Clique-Width and Directed Width Measures for Answer-Set Programming. Attending to Characters in Neural Sequence Labeling Models. Identifying Depression on Twitter. The Color of the Cat is Gray: 1 Million …

Information Processing by Nonlinear Phase Dynamics in Locally Connected Arrays


Title	Information Processing by Nonlinear Phase Dynamics in Locally Connected Arrays
Authors	Richard A. Kiehl
Abstract	Research toward powerful information processing systems that circumvent the interconnect bottleneck by exploiting the nonlinear evolution of multiple phase dynamics in locally connected arrays is discussed. We focus on a scheme in which logic states are defined by the electrical phase of a dynamic process and information processing is realized through interactions between the elements in the array. Simulation results are given for networks comprised of neuron-like integrate-and-fire elements, which could potentially be implemented by ultra-small tunnel junctions, molecules and other types of nanoscale elements. This approach could lead to powerful information processing systems due to massive parallelism in simple, highly scalable nano-architectures. The rational for this approach, its advantages, simulation results, critical issues, and future research directions are discussed.
Tasks
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06665v1
PDF	http://arxiv.org/pdf/1603.06665v1.pdf
PWC	https://paperswithcode.com/paper/information-processing-by-nonlinear-phase
Repo
Framework

Robust Optimization for Tree-Structured Stochastic Network Design


Title	Robust Optimization for Tree-Structured Stochastic Network Design
Authors	Xiaojian Wu, Akshat Kumar, Daniel Sheldon, Shlomo Zilberstein
Abstract	Stochastic network design is a general framework for optimizing network connectivity. It has several applications in computational sustainability including spatial conservation planning, pre-disaster network preparation, and river network optimization. A common assumption in previous work has been made that network parameters (e.g., probability of species colonization) are precisely known, which is unrealistic in real- world settings. We therefore address the robust river network design problem where the goal is to optimize river connectivity for fish movement by removing barriers. We assume that fish passability probabilities are known only imprecisely, but are within some interval bounds. We then develop a planning approach that computes the policies with either high robust ratio or low regret. Empirically, our approach scales well to large river networks. We also provide insights into the solutions generated by our robust approach, which has significantly higher robust ratio than the baseline solution with mean parameter estimates.
Tasks
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00104v1
PDF	http://arxiv.org/pdf/1612.00104v1.pdf
PWC	https://paperswithcode.com/paper/robust-optimization-for-tree-structured
Repo
Framework

Clique-Width and Directed Width Measures for Answer-Set Programming


Title	Clique-Width and Directed Width Measures for Answer-Set Programming
Authors	Bernhard Bliem, Sebastian Ordyniak, Stefan Woltran
Abstract	Disjunctive Answer Set Programming (ASP) is a powerful declarative programming paradigm whose main decision problems are located on the second level of the polynomial hierarchy. Identifying tractable fragments and developing efficient algorithms for such fragments are thus important objectives in order to complement the sophisticated ASP systems available to date. Hard problems can become tractable if some problem parameter is bounded by a fixed constant; such problems are then called fixed-parameter tractable (FPT). While several FPT results for ASP exist, parameters that relate to directed or signed graphs representing the program at hand have been neglected so far. In this paper, we first give some negative observations showing that directed width measures on the dependency graph of a program do not lead to FPT results. We then consider the graph parameter of signed clique-width and present a novel dynamic programming algorithm that is FPT w.r.t. this parameter. Clique-width is more general than the well-known treewidth, and, to the best of our knowledge, ours is the first FPT algorithm for bounded clique-width for reasoning problems beyond SAT.
Tasks
Published	2016-06-30
URL	http://arxiv.org/abs/1606.09449v2
PDF	http://arxiv.org/pdf/1606.09449v2.pdf
PWC	https://paperswithcode.com/paper/clique-width-and-directed-width-measures-for
Repo
Framework

Attending to Characters in Neural Sequence Labeling Models


Title	Attending to Characters in Neural Sequence Labeling Models
Authors	Marek Rei, Gamal K. O. Crichton, Sampo Pyysalo
Abstract	Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining alternative word representations. By using an attention mechanism, the model is able to dynamically decide how much information to use from a word- or character-level component. We evaluated different architectures on a range of sequence labeling datasets, and character-level extensions were found to improve performance on every benchmark. In addition, the proposed attention-based architecture delivered the best results even with a smaller number of trainable parameters.
Tasks	Chunking, Grammatical Error Detection, Named Entity Recognition, Part-Of-Speech Tagging, Word Embeddings
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04361v1
PDF	http://arxiv.org/pdf/1611.04361v1.pdf
PWC	https://paperswithcode.com/paper/attending-to-characters-in-neural-sequence
Repo
Framework

Identifying Depression on Twitter


Title	Identifying Depression on Twitter
Authors	Moin Nadeem
Abstract	Social media has recently emerged as a premier method to disseminate information online. Through these online networks, tens of millions of individuals communicate their thoughts, personal experiences, and social ideals. We therefore explore the potential of social media to predict, even prior to onset, Major Depressive Disorder (MDD) in online personas. We employ a crowdsourced method to compile a list of Twitter users who profess to being diagnosed with depression. Using up to a year of prior social media postings, we utilize a Bag of Words approach to quantify each tweet. Lastly, we leverage several statistical classifiers to provide estimates to the risk of depression. Our work posits a new methodology for constructing our classifier by treating social as a text-classification problem, rather than a behavioral one on social media platforms. By using a corpus of 2.5M tweets, we achieved an 81% accuracy rate in classification, with a precision score of .86. We believe that this method may be helpful in developing tools that estimate the risk of an individual being depressed, can be employed by physicians, concerned individuals, and healthcare agencies to aid in diagnosis, even possibly enabling those suffering from depression to be more proactive about recovering from their mental health.
Tasks	Text Classification
Published	2016-07-25
URL	http://arxiv.org/abs/1607.07384v1
PDF	http://arxiv.org/pdf/1607.07384v1.pdf
PWC	https://paperswithcode.com/paper/identifying-depression-on-twitter
Repo
Framework

The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA)


Title	The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA)
Authors	Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada
Abstract	Visual Question Answering (VQA) task has showcased a new stage of interaction between language and vision, two of the most pivotal components of artificial intelligence. However, it has mostly focused on generating short and repetitive answers, mostly single words, which fall short of rich linguistic capabilities of humans. We introduce Full-Sentence Visual Question Answering (FSVQA) dataset, consisting of nearly 1 million pairs of questions and full-sentence answers for images, built by applying a number of rule-based natural language processing techniques to original VQA dataset and captions in the MS COCO dataset. This poses many additional complexities to conventional VQA task, and we provide a baseline for approaching and evaluating the task, on top of which we invite the research community to build further improvements.
Tasks	Question Answering, Visual Question Answering
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06657v1
PDF	http://arxiv.org/pdf/1609.06657v1.pdf
PWC	https://paperswithcode.com/paper/the-color-of-the-cat-is-gray-1-million-full
Repo
Framework

Large-scale Kernel-based Feature Extraction via Budgeted Nonlinear Subspace Tracking


Title	Large-scale Kernel-based Feature Extraction via Budgeted Nonlinear Subspace Tracking
Authors	Fatemeh Sheikholeslami, Dimitris Berberidis, Georgios B. Giannakis
Abstract	Kernel-based methods enjoy powerful generalization capabilities in handling a variety of learning tasks. When such methods are provided with sufficient training data, broadly-applicable classes of nonlinear functions can be approximated with desired accuracy. Nevertheless, inherent to the nonparametric nature of kernel-based estimators are computational and memory requirements that become prohibitive with large-scale datasets. In response to this formidable challenge, the present work puts forward a low-rank, kernel-based, feature extraction approach that is particularly tailored for online operation, where data streams need not be stored in memory. A novel generative model is introduced to approximate high-dimensional (possibly infinite) features via a low-rank nonlinear subspace, the learning of which leads to a direct kernel function approximation. Offline and online solvers are developed for the subspace learning task, along with affordable versions, in which the number of stored data vectors is confined to a predefined budget. Analytical results provide performance bounds on how well the kernel matrix as well as kernel-based classification and regression tasks can be approximated by leveraging budgeted online subspace learning and feature extraction schemes. Tests on synthetic and real datasets demonstrate and benchmark the efficiency of the proposed method when linear classification and regression is applied to the extracted features.
Tasks
Published	2016-01-28
URL	http://arxiv.org/abs/1601.07947v2
PDF	http://arxiv.org/pdf/1601.07947v2.pdf
PWC	https://paperswithcode.com/paper/large-scale-kernel-based-feature-extraction
Repo
Framework

Is spoken language all-or-nothing? Implications for future speech-based human-machine interaction


Title	Is spoken language all-or-nothing? Implications for future speech-based human-machine interaction
Authors	Roger K. Moore
Abstract	Recent years have seen significant market penetration for voice-based personal assistants such as Apple’s Siri. However, despite this success, user take-up is frustratingly low. This position paper argues that there is a habitability gap caused by the inevitable mismatch between the capabilities and expectations of human users and the features and benefits provided by contemporary technology. Suggestions are made as to how such problems might be mitigated, but a more worrisome question emerges: “is spoken language all-or-nothing”? The answer, based on contemporary views on the special nature of (spoken) language, is that there may indeed be a fundamental limit to the interaction that can take place between mismatched interlocutors (such as humans and machines). However, it is concluded that interactions between native and non-native speakers, or between adults and children, or even between humans and dogs, might provide critical inspiration for the design of future speech-based human-machine interaction.
Tasks
Published	2016-07-18
URL	http://arxiv.org/abs/1607.05174v1
PDF	http://arxiv.org/pdf/1607.05174v1.pdf
PWC	https://paperswithcode.com/paper/is-spoken-language-all-or-nothing
Repo
Framework

Unsupervised Understanding of Location and Illumination Changes in Egocentric Videos


Title	Unsupervised Understanding of Location and Illumination Changes in Egocentric Videos
Authors	Alejandro Betancourt, Natalia Díaz-Rodríguez, Emilia Barakova, Lucio Marcenaro, Matthias Rauterberg, Carlo Regazzoni
Abstract	Wearable cameras stand out as one of the most promising devices for the upcoming years, and as a consequence, the demand of computer algorithms to automatically understand the videos recorded with them is increasing quickly. An automatic understanding of these videos is not an easy task, and its mobile nature implies important challenges to be faced, such as the changing light conditions and the unrestricted locations recorded. This paper proposes an unsupervised strategy based on global features and manifold learning to endow wearable cameras with contextual information regarding the light conditions and the location captured. Results show that non-linear manifold methods can capture contextual patterns from global features without compromising large computational resources. The proposed strategy is used, as an application case, as a switching mechanism to improve the hand-detection problem in egocentric videos.
Tasks
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09200v2
PDF	http://arxiv.org/pdf/1603.09200v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-understanding-of-location-and
Repo
Framework

Gabor Wavelets in Image Processing


Title	Gabor Wavelets in Image Processing
Authors	David Barina
Abstract	This work shows the use of a two-dimensional Gabor wavelets in image processing. Convolution with such a two-dimensional wavelet can be separated into two series of one-dimensional ones. The key idea of this work is to utilize a Gabor wavelet as a multiscale partial differential operator of a given order. Gabor wavelets are used here to detect edges, corners and blobs. A performance of such an interest point detector is compared to detectors utilizing a Haar wavelet and a derivative of a Gaussian function. The proposed approach may be useful when a fast implementation of the Gabor transform is available or when the transform is already precomputed.
Tasks
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03308v1
PDF	http://arxiv.org/pdf/1602.03308v1.pdf
PWC	https://paperswithcode.com/paper/gabor-wavelets-in-image-processing
Repo
Framework

Adaptive Learning with Robust Generalization Guarantees


Title	Adaptive Learning with Robust Generalization Guarantees
Authors	Rachel Cummings, Katrina Ligett, Kobbi Nissim, Aaron Roth, Zhiwei Steven Wu
Abstract	The traditional notion of generalization—i.e., learning a hypothesis whose empirical error is close to its true error—is surprisingly brittle. As has recently been noted in [DFH+15b], even if several algorithms have this guarantee in isolation, the guarantee need not hold if the algorithms are composed adaptively. In this paper, we study three notions of generalization—increasing in strength—that are robust to postprocessing and amenable to adaptive composition, and examine the relationships between them. We call the weakest such notion Robust Generalization. A second, intermediate, notion is the stability guarantee known as differential privacy. The strongest guarantee we consider we call Perfect Generalization. We prove that every hypothesis class that is PAC learnable is also PAC learnable in a robustly generalizing fashion, with almost the same sample complexity. It was previously known that differentially private algorithms satisfy robust generalization. In this paper, we show that robust generalization is a strictly weaker concept, and that there is a learning task that can be carried out subject to robust generalization guarantees, yet cannot be carried out subject to differential privacy. We also show that perfect generalization is a strictly stronger guarantee than differential privacy, but that, nevertheless, many learning tasks can be carried out subject to the guarantees of perfect generalization.
Tasks
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07726v2
PDF	http://arxiv.org/pdf/1602.07726v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-learning-with-robust-generalization
Repo
Framework

Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints


Title	Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints
Authors	Homa Foroughi, Nilanjan Ray, Hong Zhang
Abstract	In this paper, we aim at learning simultaneously a discriminative dictionary and a robust projection matrix from noisy data. The joint learning, makes the learned projection and dictionary a better fit for each other, so a more accurate classification can be obtained. However, current prevailing joint dimensionality reduction and dictionary learning methods, would fail when the training samples are noisy or heavily corrupted. To address this issue, we propose a joint projection and dictionary learning using low-rank regularization and graph constraints (JPDL-LR). Specifically, the discrimination of the dictionary is achieved by imposing Fisher criterion on the coding coefficients. In addition, our method explicitly encodes the local structure of data by incorporating a graph regularization term, that further improves the discriminative ability of the projection matrix. Inspired by recent advances of low-rank representation for removing outliers and noise, we enforce a low-rank constraint on sub-dictionaries of all classes to make them more compact and robust to noise. Experimental results on several benchmark datasets verify the effectiveness and robustness of our method for both dimensionality reduction and image classification, especially when the data contains considerable noise or variations.
Tasks	Dictionary Learning, Dimensionality Reduction, Image Classification
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07697v2
PDF	http://arxiv.org/pdf/1603.07697v2.pdf
PWC	https://paperswithcode.com/paper/joint-projection-and-dictionary-learning
Repo
Framework

Iterative Views Agreement: An Iterative Low-Rank based Structured Optimization Method to Multi-View Spectral Clustering


Title	Iterative Views Agreement: An Iterative Low-Rank based Structured Optimization Method to Multi-View Spectral Clustering
Authors	Yang Wang, Wenjie Zhang, Lin Wu, Xuemin Lin, Meng Fang, Shirui Pan
Abstract	Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matrices, is a fundamental clustering problem. Among the existing methods, Low-Rank Representation (LRR) based method is quite superior in terms of its effectiveness, intuitiveness and robustness to noise corruptions. However, it aggressively tries to learn a common low-dimensional subspace for multi-view data, while inattentively ignoring the local manifold structure in each view, which is critically important to the spectral clustering; worse still, the low-rank minimization is enforced to achieve the data correlation consensus among all views, failing to flexibly preserve the local manifold structure for each view. In this paper, 1) we propose a multi-graph laplacian regularized LRR with each graph laplacian corresponding to one view to characterize its local manifold structure. 2) Instead of directly enforcing the low-rank minimization among all views for correlation consensus, we separately impose low-rank constraint on each view, coupled with a mutual structural consensus constraint, where it is able to not only well preserve the local manifold structure but also serve as a constraint for that from other views, which iteratively makes the views more agreeable. Extensive experiments on real-world multi-view data sets demonstrate its superiority.
Tasks
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05560v1
PDF	http://arxiv.org/pdf/1608.05560v1.pdf
PWC	https://paperswithcode.com/paper/iterative-views-agreement-an-iterative-low
Repo
Framework

On Multiplicative Integration with Recurrent Neural Networks


Title	On Multiplicative Integration with Recurrent Neural Networks
Authors	Yuhuai Wu, Saizheng Zhang, Ying Zhang, Yoshua Bengio, Ruslan Salakhutdinov
Abstract	We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs). MI changes the way in which information from difference sources flows and is integrated in the computational building block of an RNN, while introducing almost no extra parameters. The new structure can be easily embedded into many popular RNN models, including LSTMs and GRUs. We empirically analyze its learning behaviour and conduct evaluations on several tasks using different RNN models. Our experimental results demonstrate that Multiplicative Integration can provide a substantial performance boost over many of the existing RNN models.
Tasks
Published	2016-06-21
URL	http://arxiv.org/abs/1606.06630v2
PDF	http://arxiv.org/pdf/1606.06630v2.pdf
PWC	https://paperswithcode.com/paper/on-multiplicative-integration-with-recurrent
Repo
Framework

A Deep Learning Approach To Multiple Kernel Fusion


Title	A Deep Learning Approach To Multiple Kernel Fusion
Authors	Huan Song, Jayaraman J. Thiagarajan, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Andreas Spanias
Abstract	Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an alternative approach that creates dense embeddings for data using the kernel similarities and adopts a deep neural network architecture for fusing the embeddings. In order to improve the effectiveness of this network, we introduce the kernel dropout regularization strategy coupled with the use of an expanded set of composition kernels. Experiment results on a real-world activity recognition dataset show that the proposed architecture is effective in fusing kernels and achieves state-of-the-art performance.
Tasks	Activity Recognition
Published	2016-12-28
URL	http://arxiv.org/abs/1612.09007v1
PDF	http://arxiv.org/pdf/1612.09007v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-approach-to-multiple-kernel
Repo
Framework