May 6, 2019

2694 words 13 mins read

Paper Group ANR 271

A Growing Long-term Episodic & Semantic Memory. Co-Occuring Directions Sketching for Approximate Matrix Multiply. A Closed Form Solution to Multi-View Low-Rank Regression. From quantum foundations via natural language meaning to a theory of everything. Semantic Parsing with Semi-Supervised Sequential Autoencoders. Generating Binary Tags for Fast Me …

A Growing Long-term Episodic & Semantic Memory


Title	A Growing Long-term Episodic & Semantic Memory
Authors	Marc Pickett, Rami Al-Rfou, Louis Shao, Chris Tar
Abstract	The long-term memory of most connectionist systems lies entirely in the weights of the system. Since the number of weights is typically fixed, this bounds the total amount of knowledge that can be learned and stored. Though this is not normally a problem for a neural network designed for a specific task, such a bound is undesirable for a system that continually learns over an open range of domains. To address this, we describe a lifelong learning system that leverages a fast, though non-differentiable, content-addressable memory which can be exploited to encode both a long history of sequential episodic knowledge and semantic knowledge over many episodes for an unbounded number of domains. This opens the door for investigation into transfer learning, and leveraging prior knowledge that has been learned over a lifetime of experiences to new domains.
Tasks	Transfer Learning
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06402v1
PDF	http://arxiv.org/pdf/1610.06402v1.pdf
PWC	https://paperswithcode.com/paper/a-growing-long-term-episodic-semantic-memory
Repo
Framework

Co-Occuring Directions Sketching for Approximate Matrix Multiply


Title	Co-Occuring Directions Sketching for Approximate Matrix Multiply
Authors	Youssef Mroueh, Etienne Marcheret, Vaibhava Goel
Abstract	We introduce co-occurring directions sketching, a deterministic algorithm for approximate matrix product (AMM), in the streaming model. We show that co-occuring directions achieves a better error bound for AMM than other randomized and deterministic approaches for AMM. Co-occurring directions gives a $1 + \epsilon$ -approximation of the optimal low rank approximation of a matrix product. Empirically our algorithm outperforms competing methods for AMM, for a small sketch size. We validate empirically our theoretical findings and algorithms
Tasks
Published	2016-10-25
URL	http://arxiv.org/abs/1610.07686v1
PDF	http://arxiv.org/pdf/1610.07686v1.pdf
PWC	https://paperswithcode.com/paper/co-occuring-directions-sketching-for
Repo
Framework

A Closed Form Solution to Multi-View Low-Rank Regression


Title	A Closed Form Solution to Multi-View Low-Rank Regression
Authors	Shuai Zheng, Xiao Cai, Chris Ding, Feiping Nie, Heng Huang
Abstract	Real life data often includes information from different channels. For example, in computer vision, we can describe an image using different image features, such as pixel intensity, color, HOG, GIST feature, SIFT features, etc.. These different aspects of the same objects are often called multi-view (or multi-modal) data. Low-rank regression model has been proved to be an effective learning mechanism by exploring the low-rank structure of real life data. But previous low-rank regression model only works on single view data. In this paper, we propose a multi-view low-rank regression model by imposing low-rank constraints on multi-view regression model. Most importantly, we provide a closed-form solution to the multi-view low-rank regression model. Extensive experiments on 4 multi-view datasets show that the multi-view low-rank regression model outperforms single-view regression model and reveals that multi-view low-rank structure is very helpful.
Tasks
Published	2016-10-14
URL	http://arxiv.org/abs/1610.04668v1
PDF	http://arxiv.org/pdf/1610.04668v1.pdf
PWC	https://paperswithcode.com/paper/a-closed-form-solution-to-multi-view-low-rank
Repo
Framework

From quantum foundations via natural language meaning to a theory of everything


Title	From quantum foundations via natural language meaning to a theory of everything
Authors	Bob Coecke
Abstract	In this paper we argue for a paradigmatic shift from `reductionism' to` togetherness’. In particular, we show how interaction between systems in quantum theory naturally carries over to modelling how word meanings interact in natural language. Since meaning in natural language, depending on the subject domain, encompasses discussions within any scientific discipline, we obtain a template for theories such as social interaction, animal behaviour, and many others.
Tasks
Published	2016-02-22
URL	http://arxiv.org/abs/1602.07618v1
PDF	http://arxiv.org/pdf/1602.07618v1.pdf
PWC	https://paperswithcode.com/paper/from-quantum-foundations-via-natural-language
Repo
Framework

Semantic Parsing with Semi-Supervised Sequential Autoencoders


Title	Semantic Parsing with Semi-Supervised Sequential Autoencoders
Authors	Tomáš Kočiský, Gábor Melis, Edward Grefenstette, Chris Dyer, Wang Ling, Phil Blunsom, Karl Moritz Hermann
Abstract	We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on domains with limited access to labelled training data and extend those datasets with synthetically generated logical forms.
Tasks	Semantic Parsing
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09315v1
PDF	http://arxiv.org/pdf/1609.09315v1.pdf
PWC	https://paperswithcode.com/paper/semantic-parsing-with-semi-supervised
Repo
Framework

Generating Binary Tags for Fast Medical Image Retrieval Based on Convolutional Nets and Radon Transform


Title	Generating Binary Tags for Fast Medical Image Retrieval Based on Convolutional Nets and Radon Transform
Authors	Xinran Liu, Hamid R. Tizhoosh, Jonathan Kofman
Abstract	Content-based image retrieval (CBIR) in large medical image archives is a challenging and necessary task. Generally, different feature extraction methods are used to assign expressive and invariant features to each image such that the search for similar images comes down to feature classification and/or matching. The present work introduces a new image retrieval method for medical applications that employs a convolutional neural network (CNN) with recently introduced Radon barcodes. We combine neural codes for global classification with Radon barcodes for the final retrieval. We also examine image search based on regions of interest (ROI) matching after image retrieval. The IRMA dataset with more than 14,000 x-rays images is used to evaluate the performance of our method. Experimental results show that our approach is superior to many published works.
Tasks	Content-Based Image Retrieval, Image Retrieval, Medical Image Retrieval
Published	2016-04-16
URL	http://arxiv.org/abs/1604.04676v1
PDF	http://arxiv.org/pdf/1604.04676v1.pdf
PWC	https://paperswithcode.com/paper/generating-binary-tags-for-fast-medical-image
Repo
Framework

Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation


Title	Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation
Authors	Yuanzhouhan Cao, Chunhua Shen, Heng Tao Shen
Abstract	Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have facilitated easy acquisition of such depth information, the vast majority of images used in vision tasks do not contain depth information. In this paper, we show that augmenting RGB images with estimated depth can also improve the accuracy of both object detection and semantic segmentation. Specifically, we first exploit the recent success of depth estimation from monocular images and learn a deep depth estimation model. Then we learn deep depth features from the estimated depth and combine with RGB features for object detection and semantic segmentation. Additionally, we propose an RGB-D semantic segmentation method which applies a multi-task training scheme: semantic label prediction and depth value regression. We test our methods on several datasets and demonstrate that incorporating information from estimated depth improves the performance of object detection and semantic segmentation remarkably.
Tasks	Depth Estimation, Object Detection, Semantic Segmentation
Published	2016-10-06
URL	http://arxiv.org/abs/1610.01706v1
PDF	http://arxiv.org/pdf/1610.01706v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-depth-from-single-monocular-images
Repo
Framework

Guidefill: GPU Accelerated, Artist Guided Geometric Inpainting for 3D Conversion


Title	Guidefill: GPU Accelerated, Artist Guided Geometric Inpainting for 3D Conversion
Authors	L. Robert Hocking, Russell MacKenzie, Carola-Bibiane Schoenlieb
Abstract	The conversion of traditional film into stereo 3D has become an important problem in the past decade. One of the main bottlenecks is a disocclusion step, which in commercial 3D conversion is usually done by teams of artists armed with a toolbox of inpainting algorithms. A current difficulty in this is that most available algorithms are either too slow for interactive use, or provide no intuitive means for users to tweak the output. In this paper we present a new fast inpainting algorithm based on transporting along automatically detected splines, which the user may edit. Our algorithm is implemented on the GPU and fills the inpainting domain in successive shells that adapt their shape on the fly. In order to allocate GPU resources as efficiently as possible, we propose a parallel algorithm to track the inpainting interface as it evolves, ensuring that no resources are wasted on pixels that are not currently being worked on. Theoretical analysis of the time and processor complexiy of our algorithm without and with tracking (as well as numerous numerical experiments) demonstrate the merits of the latter. Our transport mechanism is similar to the one used in coherence transport, but improves upon it by corrected a “kinking” phenomena whereby extrapolated isophotes may bend at the boundary of the inpainting domain. Theoretical results explaining this phenomena and its resolution are presented. Although our method ignores texture, in many cases this is not a problem due to the thin inpainting domains in 3D conversion. Experimental results show that our method can achieve a visual quality that is competitive with the state-of-the-art while maintaining interactive speeds and providing the user with an intuitive interface to tweak the results.
Tasks
Published	2016-11-16
URL	http://arxiv.org/abs/1611.05319v3
PDF	http://arxiv.org/pdf/1611.05319v3.pdf
PWC	https://paperswithcode.com/paper/guidefill-gpu-accelerated-artist-guided
Repo
Framework

Hierarchical Multi-resolution Mesh Networks for Brain Decoding


Title	Hierarchical Multi-resolution Mesh Networks for Brain Decoding
Authors	Itir Onal Ertugrul, Mete Ozay, Fatos Tunay Yarman Vural
Abstract	We propose a new framework, called Hierarchical Multi-resolution Mesh Networks (HMMNs), which establishes a set of brain networks at multiple time resolutions of fMRI signal to represent the underlying cognitive process. The suggested framework, first, decomposes the fMRI signal into various frequency subbands using wavelet transforms. Then, a brain network, called mesh network, is formed at each subband by ensembling a set of local meshes. The locality around each anatomic region is defined with respect to a neighborhood system based on functional connectivity. The arc weights of a mesh are estimated by ridge regression formed among the average region time series. In the final step, the adjacency matrices of mesh networks obtained at different subbands are ensembled for brain decoding under a hierarchical learning architecture, called, fuzzy stacked generalization (FSG). Our results on Human Connectome Project task-fMRI dataset reflect that the suggested HMMN model can successfully discriminate tasks by extracting complementary information obtained from mesh arc weights of multiple subbands. We study the topological properties of the mesh networks at different resolutions using the network measures, namely, node degree, node strength, betweenness centrality and global efficiency; and investigate the connectivity of anatomic regions, during a cognitive task. We observe significant variations among the network topologies obtained for different subbands. We, also, analyze the diversity properties of classifier ensemble, trained by the mesh networks in multiple subbands and observe that the classifiers in the ensemble collaborate with each other to fuse the complementary information freed at each subband. We conclude that the fMRI data, recorded during a cognitive task, embed diverse information across the anatomic regions at each resolution.
Tasks	Brain Decoding, Time Series
Published	2016-07-12
URL	http://arxiv.org/abs/1607.07695v2
PDF	http://arxiv.org/pdf/1607.07695v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-multi-resolution-mesh-networks
Repo
Framework

Estimating mutual information in high dimensions via classification error


Title	Estimating mutual information in high dimensions via classification error
Authors	Charles Y. Zheng, Yuval Benjamini
Abstract	Multivariate pattern analyses approaches in neuroimaging are fundamentally concerned with investigating the quantity and type of information processed by various regions of the human brain; typically, estimates of classification accuracy are used to quantify information. While a extensive and powerful library of methods can be applied to train and assess classifiers, it is not always clear how to use the resulting measures of classification performance to draw scientific conclusions: e.g. for the purpose of evaluating redundancy between brain regions. An additional confound for interpreting classification performance is the dependence of the error rate on the number and choice of distinct classes obtained for the classification task. In contrast, mutual information is a quantity defined independently of the experimental design, and has ideal properties for comparative analyses. Unfortunately, estimating the mutual information based on observations becomes statistically infeasible in high dimensions without some kind of assumption or prior. In this paper, we construct a novel classification-based estimator of mutual information based on high-dimensional asymptotics. We show that in a particular limiting regime, the mutual information is an invertible function of the expected $k$-class Bayes error. While the theory is based on a large-sample, high-dimensional limit, we demonstrate through simulations that our proposed estimator has superior performance to the alternatives in problems of moderate dimensionality.
Tasks
Published	2016-06-16
URL	http://arxiv.org/abs/1606.05229v2
PDF	http://arxiv.org/pdf/1606.05229v2.pdf
PWC	https://paperswithcode.com/paper/estimating-mutual-information-in-high
Repo
Framework

Multi-Field Structural Decomposition for Question Answering


Title	Multi-Field Structural Decomposition for Question Answering
Authors	Tomasz Jurczyk, Jinho D. Choi
Abstract	This paper presents a precursory yet novel approach to the question answering task using structural decomposition. Our system first generates linguistic structures such as syntactic and semantic trees from text, decomposes them into multiple fields, then indexes the terms in each field. For each question, it decomposes the question into multiple fields, measures the relevance score of each field to the indexed ones, then ranks all documents by their relevance scores and weights associated with the fields, where the weights are learned through statistical modeling. Our final model gives an absolute improvement of over 40% to the baseline approach using simple search for detecting documents containing answers.
Tasks	Question Answering
Published	2016-04-04
URL	http://arxiv.org/abs/1604.00938v1
PDF	http://arxiv.org/pdf/1604.00938v1.pdf
PWC	https://paperswithcode.com/paper/multi-field-structural-decomposition-for
Repo
Framework

A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting


Title	A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting
Authors	Muhammad Imran, Sanjay Chawla, Carlos Castillo
Abstract	An emerging challenge in the online classification of social media data streams is to keep the categories used for classification up-to-date. In this paper, we propose an innovative framework based on an Expert-Machine-Crowd (EMC) triad to help categorize items by continuously identifying novel concepts in heterogeneous data streams often riddled with outliers. We unify constrained clustering and outlier detection by formulating a novel optimization problem: COD-Means. We design an algorithm to solve the COD-Means problem and show that COD-Means will not only help detect novel categories but also seamlessly discover human annotation errors and improve the overall quality of the categorization process. Experiments on diverse real data sets demonstrate that our approach is both effective and efficient.
Tasks	Outlier Detection
Published	2016-10-06
URL	http://arxiv.org/abs/1610.01858v1
PDF	http://arxiv.org/pdf/1610.01858v1.pdf
PWC	https://paperswithcode.com/paper/a-robust-framework-for-classifying-evolving
Repo
Framework

Introduction: Cognitive Issues in Natural Language Processing


Title	Introduction: Cognitive Issues in Natural Language Processing
Authors	Thierry Poibeau, Shravan Vasishth
Abstract	This special issue is dedicated to get a better picture of the relationships between computational linguistics and cognitive science. It specifically raises two questions: “what is the potential contribution of computational language modeling to cognitive science?” and conversely: “what is the influence of cognitive science in contemporary computational linguistics?”
Tasks	Language Modelling
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07365v1
PDF	http://arxiv.org/pdf/1610.07365v1.pdf
PWC	https://paperswithcode.com/paper/introduction-cognitive-issues-in-natural
Repo
Framework

Concept based Attention


Title	Concept based Attention
Authors	Jie You, Xin Yang, Matthias Hub
Abstract	Attention endows animals an ability to concentrate on the most relevant information among a deluge of distractors at any given time, either through volitionally ‘top-down’ biasing, or driven by automatically ‘bottom-up’ saliency of stimuli, in favour of advantageous competition in neural modulations for information processing. Nevertheless, instead of being limited to perceive simple features, human and other advanced animals adaptively learn the world into categories and abstract concepts from experiences, imparting the world meanings. This thesis suggests that the high-level cognitive ability of human is more likely driven by attention basing on abstract perceptions, which is defined as concept based attention (CbA).
Tasks
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03416v1
PDF	http://arxiv.org/pdf/1605.03416v1.pdf
PWC	https://paperswithcode.com/paper/concept-based-attention
Repo
Framework

Effective Combination of Language and Vision Through Model Composition and the R-CCA Method


Title	Effective Combination of Language and Vision Through Model Composition and the R-CCA Method
Authors	Hagar Loeub, Roi Reichart
Abstract	We address the problem of integrating textual and visual information in vector space models for word meaning representation. We first present the Residual CCA (R-CCA) method, that complements the standard CCA method by representing, for each modality, the difference between the original signal and the signal projected to the shared, max correlation, space. We then show that constructing visual and textual representations and then post-processing them through composition of common modeling motifs such as PCA, CCA, R-CCA and linear interpolation (a.k.a sequential modeling) yields high quality models. On five standard semantic benchmarks our sequential models outperform recent multimodal representation learning alternatives, including ones that rely on joint representation learning. For two of these benchmarks our R-CCA method is part of the Best configuration our algorithm yields.
Tasks	Representation Learning
Published	2016-09-28
URL	http://arxiv.org/abs/1609.08810v2
PDF	http://arxiv.org/pdf/1609.08810v2.pdf
PWC	https://paperswithcode.com/paper/effective-combination-of-language-and-vision
Repo
Framework