May 6, 2019

2820 words 14 mins read

Paper Group ANR 420

Hybrid clustering-classification neural network in the medical diagnostics of reactive arthritis. Corralling a Band of Bandit Algorithms. Semi-supervised Word Sense Disambiguation with Neural Models. Autonomous driving challenge: To Infer the property of a dynamic object based on its motion pattern using recurrent neural network. A Predictive Model …

Hybrid clustering-classification neural network in the medical diagnostics of reactive arthritis


Title	Hybrid clustering-classification neural network in the medical diagnostics of reactive arthritis
Authors	Yevgeniy Bodyanskiy, Olena Vynokurova, Volodymyr Savvo, Tatiana Tverdokhlib, Pavlo Mulesa
Abstract	The hybrid clustering-classification neural network is proposed. This network allows increasing a quality of information processing under the condition of overlapping classes due to the rational choice of a learning rate parameter and introducing a special procedure of fuzzy reasoning in the clustering process, which occurs both with an external learning signal (supervised) and without the one (unsupervised). As similarity measure neighborhood function or membership one, cosine structures are used, which allow to provide a high flexibility due to self-learning-learning process and to provide some new useful properties. Many realized experiments have confirmed the efficiency of proposed hybrid clustering-classification neural network; also, this network was used for solving diagnostics task of reactive arthritis.
Tasks
Published	2016-10-21
URL	http://arxiv.org/abs/1610.07857v1
PDF	http://arxiv.org/pdf/1610.07857v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-clustering-classification-neural
Repo
Framework

Corralling a Band of Bandit Algorithms


Title	Corralling a Band of Bandit Algorithms
Authors	Alekh Agarwal, Haipeng Luo, Behnam Neyshabur, Robert E. Schapire
Abstract	We study the problem of combining multiple bandit algorithms (that is, online learning algorithms with partial feedback) with the goal of creating a master algorithm that performs almost as well as the best base algorithm if it were to be run on its own. The main challenge is that when run with a master, base algorithms unavoidably receive much less feedback and it is thus critical that the master not starve a base algorithm that might perform uncompetitively initially but would eventually outperform others if given enough feedback. We address this difficulty by devising a version of Online Mirror Descent with a special mirror map together with a sophisticated learning rate scheme. We show that this approach manages to achieve a more delicate balance between exploiting and exploring base algorithms than previous works yielding superior regret bounds. Our results are applicable to many settings, such as multi-armed bandits, contextual bandits, and convex bandits. As examples, we present two main applications. The first is to create an algorithm that enjoys worst-case robustness while at the same time performing much better when the environment is relatively easy. The second is to create an algorithm that works simultaneously under different assumptions of the environment, such as different priors or different loss structures.
Tasks	Multi-Armed Bandits
Published	2016-12-19
URL	http://arxiv.org/abs/1612.06246v3
PDF	http://arxiv.org/pdf/1612.06246v3.pdf
PWC	https://paperswithcode.com/paper/corralling-a-band-of-bandit-algorithms
Repo
Framework

Semi-supervised Word Sense Disambiguation with Neural Models


Title	Semi-supervised Word Sense Disambiguation with Neural Models
Authors	Dayu Yuan, Julian Richardson, Ryan Doherty, Colin Evans, Eric Altendorf
Abstract	Determining the intended sense of words in text - word sense disambiguation (WSD) - is a long standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.
Tasks	Language Modelling, Word Sense Disambiguation
Published	2016-03-22
URL	http://arxiv.org/abs/1603.07012v2
PDF	http://arxiv.org/pdf/1603.07012v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-word-sense-disambiguation-1
Repo
Framework

Autonomous driving challenge: To Infer the property of a dynamic object based on its motion pattern using recurrent neural network


Title	Autonomous driving challenge: To Infer the property of a dynamic object based on its motion pattern using recurrent neural network
Authors	Mona Fathollahi, Rangachar Kasturi
Abstract	In autonomous driving applications a critical challenge is to identify action to take to avoid an obstacle on collision course. For example, when a heavy object is suddenly encountered it is critical to stop the vehicle or change the lane even if it causes other traffic disruptions. However,there are situations when it is preferable to collide with the object rather than take an action that would result in a much more serious accident than collision with the object. For example, a heavy object which falls from a truck should be avoided whereas a bouncing ball or a soft target such as a foam box need not be.We present a novel method to discriminate between the motion characteristics of these types of objects based on their physical properties such as bounciness, elasticity, etc.In this preliminary work, we use recurrent neural net-work with LSTM cells to train a classifier to classify objects based on their motion trajectories. We test the algorithm on synthetic data, and, as a proof of concept, demonstrate its effectiveness on a limited set of real-world data.
Tasks	Autonomous Driving
Published	2016-09-01
URL	http://arxiv.org/abs/1609.00361v2
PDF	http://arxiv.org/pdf/1609.00361v2.pdf
PWC	https://paperswithcode.com/paper/autonomous-driving-challenge-to-infer-the
Repo
Framework

A Predictive Model using the Markov Property


Title	A Predictive Model using the Markov Property
Authors	Robert A. Murphy
Abstract	Given a data set of numerical values which are sampled from some unknown probability distribution, we will show how to check if the data set exhibits the Markov property and we will show how to use the Markov property to predict future values from the same distribution, with probability 1.
Tasks
Published	2016-01-08
URL	http://arxiv.org/abs/1601.01700v1
PDF	http://arxiv.org/pdf/1601.01700v1.pdf
PWC	https://paperswithcode.com/paper/a-predictive-model-using-the-markov-property
Repo
Framework

Towards an Automated Image De-fencing Algorithm Using Sparsity


Title	Towards an Automated Image De-fencing Algorithm Using Sparsity
Authors	Sankaraganesh Jonna, Krishna K. Nakka, Rajiv R. Sahay
Abstract	Conventional approaches to image de-fencing suffer from non-robust fence detection and are limited to processing images of static scenes. In this position paper, we propose an automatic de-fencing algorithm for images of dynamic scenes. We divide the problem of image de-fencing into the tasks of automated fence detection, motion estimation and fusion of data from multiple frames of a captured video of the dynamic scene. Fences are detected automatically using two approaches, namely, employing Gabor filter and a machine learning method. We cast the fence removal problem in an optimization framework, by modeling the formation of the degraded observations. The inverse problem is solved using split Bregman technique assuming total variation of the de-fenced image as the regularization constraint.
Tasks	Motion Estimation
Published	2016-12-10
URL	http://arxiv.org/abs/1612.03273v1
PDF	http://arxiv.org/pdf/1612.03273v1.pdf
PWC	https://paperswithcode.com/paper/towards-an-automated-image-de-fencing
Repo
Framework

A Shallow High-Order Parametric Approach to Data Visualization and Compression


Title	A Shallow High-Order Parametric Approach to Data Visualization and Compression
Authors	Martin Renqiang Min, Hongyu Guo, Dongjin Song
Abstract	Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We present a supervised discriminative High-Order Parametric Embedding (HOPE) approach to data visualization and compression. Compared to deep embedding models with complicated deep architectures, HOPE generates more effective high-order feature mapping through an embarrassingly simple shallow model. Furthermore, two approaches to generating a small number of exemplars conveying high-order interactions to represent large-scale data sets are proposed. These exemplars in combination with the feature mapping learned by HOPE effectively capture essential data variations. Moreover, through HOPE, these exemplars are employed to increase the computational efficiency of kNN classification for fast information retrieval by thousands of times. For classification in two-dimensional embedding space on MNIST and USPS datasets, our shallow method HOPE with simple Sigmoid transformations significantly outperforms state-of-the-art supervised deep embedding models based on deep neural networks, and even achieved historically low test error rate of 0.65% in two-dimensional space on MNIST, which demonstrates the representational efficiency and power of supervised shallow models with high-order feature interactions.
Tasks	Information Retrieval
Published	2016-08-16
URL	http://arxiv.org/abs/1608.04689v1
PDF	http://arxiv.org/pdf/1608.04689v1.pdf
PWC	https://paperswithcode.com/paper/a-shallow-high-order-parametric-approach-to
Repo
Framework

Multi-Path Feedback Recurrent Neural Network for Scene Parsing


Title	Multi-Path Feedback Recurrent Neural Network for Scene Parsing
Authors	Xiaojie Jin, Yunpeng Chen, Jiashi Feng, Zequn Jie, Shuicheng Yan
Abstract	In this paper, we consider the scene parsing problem and propose a novel Multi-Path Feedback recurrent neural network (MPF-RNN) for parsing scene images. MPF-RNN can enhance the capability of RNNs in modeling long-range context information at multiple levels and better distinguish pixels that are easy to confuse. Different from feedforward CNNs and RNNs with only single feedback, MPF-RNN propagates the contextual features learned at top layer through \textit{multiple} weighted recurrent connections to learn bottom features. For better training MPF-RNN, we propose a new strategy that considers accumulative loss at multiple recurrent steps to improve performance of the MPF-RNN on parsing small objects. With these two novel components, MPF-RNN has achieved significant improvement over strong baselines (VGG16 and Res101) on five challenging scene parsing benchmarks, including traditional SiftFlow, Barcelona, CamVid, Stanford Background as well as the recently released large-scale ADE20K.
Tasks	Scene Parsing
Published	2016-08-27
URL	http://arxiv.org/abs/1608.07706v3
PDF	http://arxiv.org/pdf/1608.07706v3.pdf
PWC	https://paperswithcode.com/paper/multi-path-feedback-recurrent-neural-network
Repo
Framework

Optimal Sensing via Multi-armed Bandit Relaxations in Mixed Observability Domains


Title	Optimal Sensing via Multi-armed Bandit Relaxations in Mixed Observability Domains
Authors	Mikko Lauri, Risto Ritala
Abstract	Sequential decision making under uncertainty is studied in a mixed observability domain. The goal is to maximize the amount of information obtained on a partially observable stochastic process under constraints imposed by a fully observable internal state. An upper bound for the optimal value function is derived by relaxing constraints. We identify conditions under which the relaxed problem is a multi-armed bandit whose optimal policy is easily computable. The upper bound is applied to prune the search space in the original problem, and the effect on solution quality is assessed via simulation experiments. Empirical results show effective pruning of the search space in a target monitoring domain.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2016-03-15
URL	http://arxiv.org/abs/1603.04586v1
PDF	http://arxiv.org/pdf/1603.04586v1.pdf
PWC	https://paperswithcode.com/paper/optimal-sensing-via-multi-armed-bandit
Repo
Framework


Title	Learning variable length units for SMT between related languages via Byte Pair Encoding
Authors	Anoop Kunchukuttan, Pushpak Bhattacharyya
Abstract	We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best performing basic units for this translation task. BPE identifies the most frequent character sequences as basic units, while orthographic syllables are linguistically motivated pseudo-syllables. We show that BPE units modestly outperform orthographic syllables as units of translation, showing up to 11% increase in BLEU score. While orthographic syllables can be used only for languages whose writing systems use vowel representations, BPE is writing system independent and we show that BPE outperforms other units for non-vowel writing systems too. Our results are supported by extensive experimentation spanning multiple language families and writing systems.
Tasks	Machine Translation
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06510v3
PDF	http://arxiv.org/pdf/1610.06510v3.pdf
PWC	https://paperswithcode.com/paper/learning-variable-length-units-for-smt
Repo
Framework

A note on the sample complexity of the Er-SpUD algorithm by Spielman, Wang and Wright for exact recovery of sparsely used dictionaries


Title	A note on the sample complexity of the Er-SpUD algorithm by Spielman, Wang and Wright for exact recovery of sparsely used dictionaries
Authors	Radosław Adamczak
Abstract	We consider the problem of recovering an invertible $n \times n$ matrix $A$ and a sparse $n \times p$ random matrix $X$ based on the observation of $Y = AX$ (up to a scaling and permutation of columns of $A$ and rows of $X$). Using only elementary tools from the theory of empirical processes we show that a version of the Er-SpUD algorithm by Spielman, Wang and Wright with high probability recovers $A$ and $X$ exactly, provided that $p \ge Cn\log n$, which is optimal up to the constant $C$.
Tasks
Published	2016-01-08
URL	http://arxiv.org/abs/1601.02049v2
PDF	http://arxiv.org/pdf/1601.02049v2.pdf
PWC	https://paperswithcode.com/paper/a-note-on-the-sample-complexity-of-the-er
Repo
Framework

Palmprint Recognition Using Deep Scattering Convolutional Network


Title	Palmprint Recognition Using Deep Scattering Convolutional Network
Authors	Shervin Minaee, Yao Wang
Abstract	Palmprint recognition has drawn a lot of attention during the recent years. Many algorithms have been proposed for palmprint recognition in the past, majority of them being based on features extracted from the transform domain. Many of these transform domain features are not translation or rotation invariant, and therefore a great deal of preprocessing is needed to align the images. In this paper, a powerful image representation, called scattering network/transform, is used for palmprint recognition. Scattering network is a convolutional network where its architecture and filters are predefined wavelet transforms. The first layer of scattering network captures similar features to SIFT descriptors and the higher-layer features capture higher-frequency content of the signal which are lost in SIFT and other similar descriptors. After extraction of the scattering features, their dimensionality is reduced by applying principal component analysis (PCA) which reduces the computational complexity of the recognition task. Two different classifiers are used for recognition: multi-class SVM and minimum-distance classifier. The proposed scheme has been tested on a well-known palmprint database and achieved accuracy rate of 99.95% and 100% using minimum distance classifier and SVM respectively.
Tasks
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09027v1
PDF	http://arxiv.org/pdf/1603.09027v1.pdf
PWC	https://paperswithcode.com/paper/palmprint-recognition-using-deep-scattering
Repo
Framework

Multi-resolution Compressive Sensing Reconstruction


Title	Multi-resolution Compressive Sensing Reconstruction
Authors	Adriana Gonzalez, Hong Jiang, Gang Huang, Laurent Jacques
Abstract	We consider the problem of reconstructing an image from compressive measurements using a multi-resolution grid. In this context, the reconstructed image is divided into multiple regions, each one with a different resolution. This problem arises in situations where the image to reconstruct contains a certain region of interest (RoI) that is more important than the rest. Through a theoretical analysis and simulation experiments we show that the multi-resolution reconstruction provides a higher quality of the RoI compared to the traditional single-resolution approach.
Tasks	Compressive Sensing
Published	2016-02-18
URL	http://arxiv.org/abs/1602.05941v1
PDF	http://arxiv.org/pdf/1602.05941v1.pdf
PWC	https://paperswithcode.com/paper/multi-resolution-compressive-sensing
Repo
Framework

SemiContour: A Semi-supervised Learning Approach for Contour Detection


Title	SemiContour: A Semi-supervised Learning Approach for Contour Detection
Authors	Zizhao Zhang, Fuyong Xing, Xiaoshuang Shi, Lin Yang
Abstract	Supervised contour detection methods usually require many labeled training images to obtain satisfactory performance. However, a large set of annotated data might be unavailable or extremely labor intensive. In this paper, we investigate the usage of semi-supervised learning (SSL) to obtain competitive detection accuracy with very limited training data (three labeled images). Specifically, we propose a semi-supervised structured ensemble learning approach for contour detection built on structured random forests (SRF). To allow SRF to be applicable to unlabeled data, we present an effective sparse representation approach to capture inherent structure in image patches by finding a compact and discriminative low-dimensional subspace representation in an unsupervised manner, enabling the incorporation of abundant unlabeled patches with their estimated structured labels to help SRF perform better node splitting. We re-examine the role of sparsity and propose a novel and fast sparse coding algorithm to boost the overall learning efficiency. To the best of our knowledge, this is the first attempt to apply SSL for contour detection. Extensive experiments on the BSDS500 segmentation dataset and the NYU Depth dataset demonstrate the superiority of the proposed method.
Tasks	Contour Detection
Published	2016-05-17
URL	http://arxiv.org/abs/1605.04996v1
PDF	http://arxiv.org/pdf/1605.04996v1.pdf
PWC	https://paperswithcode.com/paper/semicontour-a-semi-supervised-learning
Repo
Framework

Learning without recall in directed circles and rooted trees


Title	Learning without recall in directed circles and rooted trees
Authors	M. Amin Rahimian, Ali Jadbabaie
Abstract	This work investigates the case of a network of agents that attempt to learn some unknown state of the world amongst the finitely many possibilities. At each time step, agents all receive random, independently distributed private signals whose distributions are dependent on the unknown state of the world. However, it may be the case that some or any of the agents cannot distinguish between two or more of the possible states based only on their private observations, as when several states result in the same distribution of the private signals. In our model, the agents form some initial belief (probability distribution) about the unknown state and then refine their beliefs in accordance with their private observations, as well as the beliefs of their neighbors. An agent learns the unknown state when her belief converges to a point mass that is concentrated at the true state. A rational agent would use the Bayes’ rule to incorporate her neighbors’ beliefs and own private signals over time. While such repeated applications of the Bayes’ rule in networks can become computationally intractable, in this paper, we show that in the canonical cases of directed star, circle or path networks and their combinations, one can derive a class of memoryless update rules that replicate that of a single Bayesian agent but replace the self beliefs with the beliefs of the neighbors. This way, one can realize an exponentially fast rate of learning similar to the case of Bayesian (fully rational) agents. The proposed rules are a special case of the Learning without Recall.
Tasks
Published	2016-11-27
URL	http://arxiv.org/abs/1611.08791v1
PDF	http://arxiv.org/pdf/1611.08791v1.pdf
PWC	https://paperswithcode.com/paper/learning-without-recall-in-directed-circles
Repo
Framework