May 5, 2019

3036 words 15 mins read

Paper Group ANR 454

Efficient Stochastic Inference of Bitwise Deep Neural Networks. Cross-model convolutional neural network for multiple modality data representation. Fashion DNA: Merging Content and Sales Data for Recommendation and Article Mapping. Transition-based Parsing with Context Enhancement and Future Reward Reranking. Zero-resource Machine Translation by Mu …

Efficient Stochastic Inference of Bitwise Deep Neural Networks


Title	Efficient Stochastic Inference of Bitwise Deep Neural Networks
Authors	Sebastian Vogel, Christoph Schorn, Andre Guntoro, Gerd Ascheid
Abstract	Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled network models to increase performance figures of bitwise neural networks in terms of classification accuracy at inference. Our experiments with the CIFAR-10 and GTSRB datasets show that the performance of such network ensembles surpasses the performance of the high-precision base model. With this technique we achieve 5.81% best classification error on CIFAR-10 test set using bitwise networks. Concerning inference on embedded systems we evaluate these bitwise networks using a hardware efficient stochastic rounding procedure. Our work contributes to efficient embedded bitwise neural networks.
Tasks
Published	2016-11-20
URL	http://arxiv.org/abs/1611.06539v1
PDF	http://arxiv.org/pdf/1611.06539v1.pdf
PWC	https://paperswithcode.com/paper/efficient-stochastic-inference-of-bitwise
Repo
Framework

Cross-model convolutional neural network for multiple modality data representation


Title	Cross-model convolutional neural network for multiple modality data representation
Authors	Yanbin Wu, Li Wang, Fan Cui, Hongbin Zhai, Baoming Dong, Jim Jing-Yan Wang
Abstract	A novel data representation method of convolutional neural net- work (CNN) is proposed in this paper to represent data of different modalities. We learn a CNN model for the data of each modality to map the data of differ- ent modalities to a common space, and regularize the new representations in the common space by a cross-model relevance matrix. We further impose that the class label of data points can also be predicted from the CNN representa- tions in the common space. The learning problem is modeled as a minimiza- tion problem, which is solved by an augmented Lagrange method (ALM) with updating rules of Alternating direction method of multipliers (ADMM). The experiments over benchmark of sequence data of multiple modalities show its advantage.
Tasks
Published	2016-11-19
URL	http://arxiv.org/abs/1611.06306v1
PDF	http://arxiv.org/pdf/1611.06306v1.pdf
PWC	https://paperswithcode.com/paper/cross-model-convolutional-neural-network-for
Repo
Framework

Fashion DNA: Merging Content and Sales Data for Recommendation and Article Mapping


Title	Fashion DNA: Merging Content and Sales Data for Recommendation and Article Mapping
Authors	Christian Bracher, Sebastian Heinz, Roland Vollgraf
Abstract	We present a method to determine Fashion DNA, coordinate vectors locating fashion items in an abstract space. Our approach is based on a deep neural network architecture that ingests curated article information such as tags and images, and is trained to predict sales for a large set of frequent customers. In the process, a dual space of customer style preferences naturally arises. Interpretation of the metric of these spaces is straightforward: The product of Fashion DNA and customer style vectors yields the forecast purchase likelihood for the customer-item pair, while the angle between Fashion DNA vectors is a measure of item similarity. Importantly, our models are able to generate unbiased purchase probabilities for fashion items based solely on article information, even in absence of sales data, thus circumventing the “cold-start problem” of collaborative recommendation approaches. Likewise, it generalizes easily and reliably to customers outside the training set. We experiment with Fashion DNA models based on visual and/or tag item data, evaluate their recommendation power, and discuss the resulting article similarities.
Tasks
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02489v1
PDF	http://arxiv.org/pdf/1609.02489v1.pdf
PWC	https://paperswithcode.com/paper/fashion-dna-merging-content-and-sales-data
Repo
Framework

Transition-based Parsing with Context Enhancement and Future Reward Reranking


Title	Transition-based Parsing with Context Enhancement and Future Reward Reranking
Authors	Fugen Zhou, Fuxiang Wu, Zhengchen Zhang, Minghui Dong
Abstract	This paper presents a novel reranking model, future reward reranking, to re-score the actions in a transition-based parser by using a global scorer. Different to conventional reranking parsing, the model searches for the best dependency tree in all feasible trees constraining by a sequence of actions to get the future reward of the sequence. The scorer is based on a first-order graph-based parser with bidirectional LSTM, which catches different parsing view compared with the transition-based parser. Besides, since context enhancement has shown substantial improvement in the arc-stand transition-based parsing over the parsing accuracy, we implement context enhancement on an arc-eager transition-base parser with stack LSTMs, the dynamic oracle and dropout supporting and achieve further improvement. With the global scorer and context enhancement, the results show that UAS of the parser increases as much as 1.20% for English and 1.66% for Chinese, and LAS increases as much as 1.32% for English and 1.63% for Chinese. Moreover, we get state-of-the-art LASs, achieving 87.58% for Chinese and 93.37% for English.
Tasks
Published	2016-12-15
URL	http://arxiv.org/abs/1612.05131v1
PDF	http://arxiv.org/pdf/1612.05131v1.pdf
PWC	https://paperswithcode.com/paper/transition-based-parsing-with-context
Repo
Framework

Zero-resource Machine Translation by Multimodal Encoder-decoder Network with Multimedia Pivot


Title	Zero-resource Machine Translation by Multimodal Encoder-decoder Network with Multimedia Pivot
Authors	Hideki Nakayama, Noriki Nishida
Abstract	We propose an approach to build a neural machine translation system with no supervised resources (i.e., no parallel corpora) using multimodal embedded representation over texts and images. Based on the assumption that text documents are often likely to be described with other multimedia information (e.g., images) somewhat related to the content, we try to indirectly estimate the relevance between two languages. Using multimedia as the “pivot”, we project all modalities into one common hidden space where samples belonging to similar semantic concepts should come close to each other, whatever the observed space of each sample is. This modality-agnostic representation is the key to bridging the gap between different modalities. Putting a decoder on top of it, our network can flexibly draw the outputs from any input modality. Notably, in the testing phase, we need only source language texts as the input for translation. In experiments, we tested our method on two benchmarks to show that it can achieve reasonable translation performance. We compared and investigated several possible implementations and found that an end-to-end model that simultaneously optimized both rank loss in multimodal encoders and cross-entropy loss in decoders performed the best.
Tasks	Machine Translation
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04503v3
PDF	http://arxiv.org/pdf/1611.04503v3.pdf
PWC	https://paperswithcode.com/paper/zero-resource-machine-translation-by
Repo
Framework

Grid Based Nonlinear Filtering Revisited: Recursive Estimation & Asymptotic Optimality


Title	Grid Based Nonlinear Filtering Revisited: Recursive Estimation & Asymptotic Optimality
Authors	Dionysios S. Kalogerias, Athina P. Petropulu
Abstract	We revisit the development of grid based recursive approximate filtering of general Markov processes in discrete time, partially observed in conditionally Gaussian noise. The grid based filters considered rely on two types of state quantization: The \textit{Markovian} type and the \textit{marginal} type. We propose a set of novel, relaxed sufficient conditions, ensuring strong and fully characterized pathwise convergence of these filters to the respective MMSE state estimator. In particular, for marginal state quantizations, we introduce the notion of \textit{conditional regularity of stochastic kernels}, which, to the best of our knowledge, constitutes the most relaxed condition proposed, under which asymptotic optimality of the respective grid based filters is guaranteed. Further, we extend our convergence results, including filtering of bounded and continuous functionals of the state, as well as recursive approximate state prediction. For both Markovian and marginal quantizations, the whole development of the respective grid based filters relies more on linear-algebraic techniques and less on measure theoretic arguments, making the presentation considerably shorter and technically simpler.
Tasks	Quantization
Published	2016-04-10
URL	http://arxiv.org/abs/1604.02631v1
PDF	http://arxiv.org/pdf/1604.02631v1.pdf
PWC	https://paperswithcode.com/paper/grid-based-nonlinear-filtering-revisited
Repo
Framework

SCOPE: Scalable Composite Optimization for Learning on Spark


Title	SCOPE: Scalable Composite Optimization for Learning on Spark
Authors	Shen-Yi Zhao, Ru Xiang, Ying-Hao Shi, Peng Gao, Wu-Jun Li
Abstract	Many machine learning models, such as logistic regression~(LR) and support vector machine~(SVM), can be formulated as composite optimization problems. Recently, many distributed stochastic optimization~(DSO) methods have been proposed to solve the large-scale composite optimization problems, which have shown better performance than traditional batch methods. However, most of these DSO methods are not scalable enough. In this paper, we propose a novel DSO method, called \underline{s}calable \underline{c}omposite \underline{op}timization for l\underline{e}arning~({SCOPE}), and implement it on the fault-tolerant distributed platform \mbox{Spark}. SCOPE is both computation-efficient and communication-efficient. Theoretical analysis shows that SCOPE is convergent with linear convergence rate when the objective function is convex. Furthermore, empirical results on real datasets show that SCOPE can outperform other state-of-the-art distributed learning methods on Spark, including both batch learning methods and DSO methods.
Tasks	Stochastic Optimization
Published	2016-01-30
URL	http://arxiv.org/abs/1602.00133v5
PDF	http://arxiv.org/pdf/1602.00133v5.pdf
PWC	https://paperswithcode.com/paper/scope-scalable-composite-optimization-for
Repo
Framework

Proceedings of the 5th Workshop on Machine Learning and Interpretation in Neuroimaging (MLINI) at NIPS 2015


Title	Proceedings of the 5th Workshop on Machine Learning and Interpretation in Neuroimaging (MLINI) at NIPS 2015
Authors	I. Rish, L. Wehbe, G. Langs, M. Grosse-Wentrup, B. Murphy, G. Cecchi
Abstract	This volume is a collection of contributions from the 5th Workshop on Machine Learning and Interpretation in Neuroimaging (MLINI) at the Neural Information Processing Systems (NIPS 2015) conference. Modern multivariate statistical methods developed in the rapidly growing field of machine learning are being increasingly applied to various problems in neuroimaging, from cognitive state detection to clinical diagnosis and prognosis. Multivariate pattern analysis methods are designed to examine complex relationships between high-dimensional signals, such as brain images, and outcomes of interest, such as the category of a stimulus, a type of a mental state of a subject, or a specific mental disorder. Such techniques are in contrast with the traditional mass-univariate approaches that dominated neuroimaging in the past and treated each individual imaging measurement in isolation. We believe that machine learning has a prominent role in shaping how questions in neuroscience are framed, and that the machine-learning mind set is now entering modern psychology and behavioral studies. It is also equally important that practical applications in these fields motivate a rapidly evolving line or research in the machine learning community. In parallel, there is an intense interest in learning more about brain function in the context of rich naturalistic environments and scenes. Efforts to go beyond highly specific paradigms that pinpoint a single function, towards schemes for measuring the interaction with natural and more varied scene are made. The goal of the workshop is to pinpoint the most pressing issues and common challenges across the neuroscience, neuroimaging, psychology and machine learning fields, and to sketch future directions and open questions in the light of novel methodology.
Tasks
Published	2016-05-14
URL	http://arxiv.org/abs/1605.04435v1
PDF	http://arxiv.org/pdf/1605.04435v1.pdf
PWC	https://paperswithcode.com/paper/proceedings-of-the-5th-workshop-on-machine
Repo
Framework

Incremental Real-Time Multibody VSLAM with Trajectory Optimization Using Stereo Camera


Title	Incremental Real-Time Multibody VSLAM with Trajectory Optimization Using Stereo Camera
Authors	N Dinesh Reddy, Iman Abbasnejad, Sheetal Reddy, Amit Kumar Mondal, Vindhya Devalla
Abstract	Real time outdoor navigation in highly dynamic environments is an crucial problem. The recent literature on real time static SLAM don’t scale up to dynamic outdoor environments. Most of these methods assume moving objects as outliers or discard the information provided by them. We propose an algorithm to jointly infer the camera trajectory and the moving object trajectory simultaneously. In this paper, we perform a sparse scene flow based motion segmentation using a stereo camera. The segmented objects motion models are used for accurate localization of the camera trajectory as well as the moving objects. We exploit the relationship between moving objects for improving the accuracy of the poses. We formulate the poses as a factor graph incorporating all the constraints. We achieve exact incremental solution by solving a full nonlinear optimization problem in real time. The evaluation is performed on the challenging KITTI dataset with multiple moving cars.Our method outperforms the previous baselines in outdoor navigation.
Tasks	Motion Segmentation
Published	2016-08-02
URL	http://arxiv.org/abs/1608.01024v1
PDF	http://arxiv.org/pdf/1608.01024v1.pdf
PWC	https://paperswithcode.com/paper/incremental-real-time-multibody-vslam-with
Repo
Framework

Go With the Flow, on Jupiter and Snow. Coherence From Model-Free Video Data without Trajectories


Title	Go With the Flow, on Jupiter and Snow. Coherence From Model-Free Video Data without Trajectories
Authors	Abd AlRahman AlMomani, Erik M. Bollt
Abstract	Viewing a data set such as the clouds of Jupiter, coherence is readily apparent to human observers, especially the Great Red Spot, but also other great storms and persistent structures. There are now many different definitions and perspectives mathematically describing coherent structures, but we will take an image processing perspective here. We describe an image processing perspective inference of coherent sets from a fluidic system directly from image data, without attempting to first model underlying flow fields, related to a concept in image processing called motion tracking. In contrast to standard spectral methods for image processing which are generally related to a symmetric affinity matrix, leading to standard spectral graph theory, we need a not symmetric affinity which arises naturally from the underlying arrow of time. We develop an anisotropic, directed diffusion operator corresponding to flow on a directed graph, from a directed affinity matrix developed with coherence in mind, and corresponding spectral graph theory from the graph Laplacian. Our methodology is not offered as more accurate than other traditional methods of finding coherent sets, but rather our approach works with alternative kinds of data sets, in the absence of vector field. Our examples will include partitioning the weather and cloud structures of Jupiter, and a local to Potsdam, N.Y. lake-effect snow event on Earth, as well as the benchmark test double-gyre system.
Tasks
Published	2016-08-25
URL	http://arxiv.org/abs/1610.01857v3
PDF	http://arxiv.org/pdf/1610.01857v3.pdf
PWC	https://paperswithcode.com/paper/go-with-the-flow-on-jupiter-and-snow
Repo
Framework

SweLL on the rise: Swedish Learner Language corpus for European Reference Level studies


Title	SweLL on the rise: Swedish Learner Language corpus for European Reference Level studies
Authors	Elena Volodina, Ildikó Pilán, Ingegerd Enström, Lorena Llozhi, Peter Lundkvist, Gunlög Sundberg, Monica Sandell
Abstract	We present a new resource for Swedish, SweLL, a corpus of Swedish Learner essays linked to learners’ performance according to the Common European Framework of Reference (CEFR). SweLL consists of three subcorpora - SpIn, SW1203 and Tisus, collected from three different educational establishments. The common metadata for all subcorpora includes age, gender, native languages, time of residence in Sweden, type of written task. Depending on the subcorpus, learner texts may contain additional information, such as text genres, topics, grades. Five of the six CEFR levels are represented in the corpus: A1, A2, B1, B2 and C1 comprising in total 339 essays. C2 level is not included since courses at C2 level are not offered. The work flow consists of collection of essays and permits, essay digitization and registration, meta-data annotation, automatic linguistic annotation. Inter-rater agreement is presented on the basis of SW1203 subcorpus. The work on SweLL is still ongoing with more than 100 essays waiting in the pipeline. This article both describes the resource and the “how-to” behind the compilation of SweLL.
Tasks
Published	2016-04-22
URL	http://arxiv.org/abs/1604.06583v1
PDF	http://arxiv.org/pdf/1604.06583v1.pdf
PWC	https://paperswithcode.com/paper/swell-on-the-rise-swedish-learner-language
Repo
Framework

Efficient Second Order Online Learning by Sketching


Title	Efficient Second Order Online Learning by Sketching
Authors	Haipeng Luo, Alekh Agarwal, Nicolo Cesa-Bianchi, John Langford
Abstract	We propose Sketched Online Newton (SON), an online second order learning algorithm that enjoys substantially improved regret guarantees for ill-conditioned data. SON is an enhanced version of the Online Newton Step, which, via sketching techniques enjoys a running time linear in the dimension and sketch size. We further develop sparse forms of the sketching methods (such as Oja’s rule), making the computation linear in the sparsity of features. Together, the algorithm eliminates all computational obstacles in previous second order online learning approaches.
Tasks
Published	2016-02-06
URL	http://arxiv.org/abs/1602.02202v4
PDF	http://arxiv.org/pdf/1602.02202v4.pdf
PWC	https://paperswithcode.com/paper/efficient-second-order-online-learning-by
Repo
Framework

Gaussian process regression can turn non-uniform and undersampled diffusion MRI data into diffusion spectrum imaging


Title	Gaussian process regression can turn non-uniform and undersampled diffusion MRI data into diffusion spectrum imaging
Authors	Jens Sjölund, Anders Eklund, Evren Özarslan, Hans Knutsson
Abstract	We propose to use Gaussian process regression to accurately estimate the diffusion MRI signal at arbitrary locations in q-space. By estimating the signal on a grid, we can do synthetic diffusion spectrum imaging: reconstructing the ensemble averaged propagator (EAP) by an inverse Fourier transform. We also propose an alternative reconstruction method guaranteeing a nonnegative EAP that integrates to unity. The reconstruction is validated on data simulated from two Gaussians at various crossing angles. Moreover, we demonstrate on non-uniformly sampled in vivo data that the method is far superior to linear interpolation, and allows a drastic undersampling of the data with only a minor loss of accuracy. We envision the method as a potential replacement for standard diffusion spectrum imaging, in particular when acquistion time is limited.
Tasks
Published	2016-11-09
URL	http://arxiv.org/abs/1611.02869v1
PDF	http://arxiv.org/pdf/1611.02869v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-regression-can-turn-non
Repo
Framework

Intrinsic Light Field Images


Title	Intrinsic Light Field Images
Authors	Elena Garces, Jose I. Echevarria, Wen Zhang, Hongzhi Wu, Kun Zhou, Diego Gutierrez
Abstract	We present a method to automatically decompose a light field into its intrinsic shading and albedo components. Contrary to previous work targeted to 2D single images and videos, a light field is a 4D structure that captures non-integrated incoming radiance over a discrete angular domain. This higher dimensionality of the problem renders previous state-of-the-art algorithms impractical either due to their cost of processing a single 2D slice, or their inability to enforce proper coherence in additional dimensions. We propose a new decomposition algorithm that jointly optimizes the whole light field data for proper angular coherence. For efficiency, we extend Retinex theory, working on the gradient domain, where new albedo and occlusion terms are introduced. Results show our method provides 4D intrinsic decompositions difficult to achieve with previous state-of-the-art algorithms. We further provide a comprehensive analysis and comparisons with existing intrinsic image/video decomposition methods on light field images.
Tasks
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04342v2
PDF	http://arxiv.org/pdf/1608.04342v2.pdf
PWC	https://paperswithcode.com/paper/intrinsic-light-field-images
Repo
Framework

Method of Tibetan Person Knowledge Extraction


Title	Method of Tibetan Person Knowledge Extraction
Authors	Yuan Sun, Zhen Zhu
Abstract	Person knowledge extraction is the foundation of the Tibetan knowledge graph construction, which provides support for Tibetan question answering system, information retrieval, information extraction and other researches, and promotes national unity and social stability. This paper proposes a SVM and template based approach to Tibetan person knowledge extraction. Through constructing the training corpus, we build the templates based the shallow parsing analysis of Tibetan syntactic, semantic features and verbs. Using the training corpus, we design a hierarchical SVM classifier to realize the entity knowledge extraction. Finally, experimental results prove the method has greater improvement in Tibetan person knowledge extraction.
Tasks	graph construction, Information Retrieval, Question Answering
Published	2016-04-11
URL	http://arxiv.org/abs/1604.02843v1
PDF	http://arxiv.org/pdf/1604.02843v1.pdf
PWC	https://paperswithcode.com/paper/method-of-tibetan-person-knowledge-extraction
Repo
Framework