May 5, 2019

3210 words 16 mins read

Paper Group ANR 541

Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks. How Deep is the Feature Analysis underlying Rapid Visual Categorization?. “What happens if…” Learning to Predict the Effect of Forces in Images. A Fully Convolutional Neural Network based Structured Prediction Approach Towards the Retinal Vessel Segmentation. SAM: Support Vec …

Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks


Title	Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
Authors	Yun-Nung Chen, Dilek Hakkani-Tur, Gokhan Tur, Asli Celikyilmaz, Jianfeng Gao, Li Deng
Abstract	Natural language understanding (NLU) is a core component of a spoken dialogue system. Recently recurrent neural networks (RNN) obtained strong results on NLU due to their superior ability of preserving sequential information over time. Traditionally, the NLU module tags semantic slots for utterances considering their flat structures, as the underlying RNN structure is a linear chain. However, natural language exhibits linguistic properties that provide rich, structured information for better understanding. This paper introduces a novel model, knowledge-guided structural attention networks (K-SAN), a generalization of RNN to additionally incorporate non-flat network topologies guided by prior knowledge. There are two characteristics: 1) important substructures can be captured from small training data, allowing the model to generalize to previously unseen test data; 2) the model automatically figures out the salient substructures that are essential to predict the semantic tags of the given sentences, so that the understanding performance can be improved. The experiments on the benchmark Air Travel Information System (ATIS) data show that the proposed K-SAN architecture can effectively extract salient knowledge from substructures with an attention mechanism, and outperform the performance of the state-of-the-art neural network based frameworks.
Tasks
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03286v1
PDF	http://arxiv.org/pdf/1609.03286v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-as-a-teacher-knowledge-guided
Repo
Framework

How Deep is the Feature Analysis underlying Rapid Visual Categorization?


Title	How Deep is the Feature Analysis underlying Rapid Visual Categorization?
Authors	Sven Eberhardt, Jonah Cader, Thomas Serre
Abstract	Rapid categorization paradigms have a long history in experimental psychology: Characterized by short presentation times and speedy behavioral responses, these tasks highlight the efficiency with which our visual system processes natural object categories. Previous studies have shown that feed-forward hierarchical models of the visual cortex provide a good fit to human visual decisions. At the same time, recent work in computer vision has demonstrated significant gains in object recognition accuracy with increasingly deep hierarchical architectures. But it is unclear how well these models account for human visual decisions and what they may reveal about the underlying brain processes. We have conducted a large-scale psychophysics study to assess the correlation between computational models and human participants on a rapid animal vs. non-animal categorization task. We considered visual representations of varying complexity by analyzing the output of different stages of processing in three state-of-the-art deep networks. We found that recognition accuracy increases with higher stages of visual processing (higher level stages indeed outperforming human participants on the same task) but that human decisions agree best with predictions from intermediate stages. Overall, these results suggest that human participants may rely on visual features of intermediate complexity and that the complexity of visual representations afforded by modern deep network models may exceed those used by human participants during rapid categorization.
Tasks	Object Recognition
Published	2016-06-03
URL	http://arxiv.org/abs/1606.01167v1
PDF	http://arxiv.org/pdf/1606.01167v1.pdf
PWC	https://paperswithcode.com/paper/how-deep-is-the-feature-analysis-underlying
Repo
Framework

“What happens if…” Learning to Predict the Effect of Forces in Images


Title	“What happens if…” Learning to Predict the Effect of Forces in Images
Authors	Roozbeh Mottaghi, Mohammad Rastegari, Abhinav Gupta, Ali Farhadi
Abstract	What happens if one pushes a cup sitting on a table toward the edge of the table? How about pushing a desk against a wall? In this paper, we study the problem of understanding the movements of objects as a result of applying external forces to them. For a given force vector applied to a specific location in an image, our goal is to predict long-term sequential movements caused by that force. Doing so entails reasoning about scene geometry, objects, their attributes, and the physical rules that govern the movements of objects. We design a deep neural network model that learns long-term sequential dependencies of object movements while taking into account the geometry and appearance of the scene by combining Convolutional and Recurrent Neural Networks. Training our model requires a large-scale dataset of object movements caused by external forces. To build a dataset of forces in scenes, we reconstructed all images in SUN RGB-D dataset in a physics simulator to estimate the physical movements of objects caused by external forces applied to them. Our Forces in Scenes (ForScene) dataset contains 10,335 images in which a variety of external forces are applied to different types of objects resulting in more than 65,000 object movements represented in 3D. Our experimental evaluations show that the challenging task of predicting long-term movements of objects as their reaction to external forces is possible from a single image.
Tasks
Published	2016-03-17
URL	http://arxiv.org/abs/1603.05600v1
PDF	http://arxiv.org/pdf/1603.05600v1.pdf
PWC	https://paperswithcode.com/paper/what-happens-if-learning-to-predict-the
Repo
Framework

A Fully Convolutional Neural Network based Structured Prediction Approach Towards the Retinal Vessel Segmentation


Title	A Fully Convolutional Neural Network based Structured Prediction Approach Towards the Retinal Vessel Segmentation
Authors	Avijit Dasgupta, Sonam Singh
Abstract	Automatic segmentation of retinal blood vessels from fundus images plays an important role in the computer aided diagnosis of retinal diseases. The task of blood vessel segmentation is challenging due to the extreme variations in morphology of the vessels against noisy background. In this paper, we formulate the segmentation task as a multi-label inference task and utilize the implicit advantages of the combination of convolutional neural networks and structured prediction. Our proposed convolutional neural network based model achieves strong performance and significantly outperforms the state-of-the-art for automatic retinal blood vessel segmentation on DRIVE dataset with 95.33% accuracy and 0.974 AUC score.
Tasks	Retinal Vessel Segmentation, Structured Prediction
Published	2016-11-07
URL	http://arxiv.org/abs/1611.02064v2
PDF	http://arxiv.org/pdf/1611.02064v2.pdf
PWC	https://paperswithcode.com/paper/a-fully-convolutional-neural-network-based
Repo
Framework

SAM: Support Vector Machine Based Active Queue Management


Title	SAM: Support Vector Machine Based Active Queue Management
Authors	Muhammad Saleh Shah, Asim Imdad Wagan, Mukhtiar Ali Unar
Abstract	Recent years have seen an increasing interest in the design of AQM (Active Queue Management) controllers. The purpose of these controllers is to manage the network congestion under varying loads, link delays and bandwidth. In this paper, a new AQM controller is proposed which is trained by using the SVM (Support Vector Machine) with the RBF (Radial Basis Function) kernal. The proposed controller is called the support vector based AQM (SAM) controller. The performance of the proposed controller has been compared with three conventional AQM controllers, namely the Random Early Detection, Blue and Proportional Plus Integral Controller. The preliminary simulation studies show that the performance of the proposed controller is comparable to the conventional controllers. However, the proposed controller is more efficient in controlling the queue size than the conventional controllers.
Tasks
Published	2016-04-02
URL	http://arxiv.org/abs/1604.00557v1
PDF	http://arxiv.org/pdf/1604.00557v1.pdf
PWC	https://paperswithcode.com/paper/sam-support-vector-machine-based-active-queue
Repo
Framework

Sampling Requirements for Stable Autoregressive Estimation


Title	Sampling Requirements for Stable Autoregressive Estimation
Authors	Abbas Kazemipour, Sina Miran, Piya Pal, Behtash Babadi, Min Wu
Abstract	We consider the problem of estimating the parameters of a linear univariate autoregressive model with sub-Gaussian innovations from a limited sequence of consecutive observations. Assuming that the parameters are compressible, we analyze the performance of the $\ell_1$-regularized least squares as well as a greedy estimator of the parameters and characterize the sampling trade-offs required for stable recovery in the non-asymptotic regime. In particular, we show that for a fixed sparsity level, stable recovery of AR parameters is possible when the number of samples scale sub-linearly with the AR order. Our results improve over existing sampling complexity requirements in AR estimation using the LASSO, when the sparsity level scales faster than the square root of the model order. We further derive sufficient conditions on the sparsity level that guarantee the minimax optimality of the $\ell_1$-regularized least squares estimate. Applying these techniques to simulated data as well as real-world datasets from crude oil prices and traffic speed data confirm our predicted theoretical performance gains in terms of estimation accuracy and model selection.
Tasks	Model Selection
Published	2016-05-04
URL	http://arxiv.org/abs/1605.01436v2
PDF	http://arxiv.org/pdf/1605.01436v2.pdf
PWC	https://paperswithcode.com/paper/sampling-requirements-for-stable
Repo
Framework

Network-regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery


Title	Network-regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery
Authors	Wenwen Min, Juan Liu, Shihua Zhang
Abstract	Molecular profiling data (e.g., gene expression) has been used for clinical risk prediction and biomarker discovery. However, it is necessary to integrate other prior knowledge like biological pathways or gene interaction networks to improve the predictive ability and biological interpretability of biomarkers. Here, we first introduce a general regularized Logistic Regression (LR) framework with regularized term $\lambda \bm{w}_1 + \eta\bm{w}^T\bm{M}\bm{w}$, which can reduce to different penalties, including Lasso, elastic net, and network-regularized terms with different $\bm{M}$. This framework can be easily solved in a unified manner by a cyclic coordinate descent algorithm which can avoid inverse matrix operation and accelerate the computing speed. However, if those estimated $\bm{w}_i$ and $\bm{w}_j$ have opposite signs, then the traditional network-regularized penalty may not perform well. To address it, we introduce a novel network-regularized sparse LR model with a new penalty $\lambda \bm{w}_1 + \eta\bm{w}^T\bm{M}\bm{w}$ to consider the difference between the absolute values of the coefficients. And we develop two efficient algorithms to solve it. Finally, we test our methods and compare them with the related ones using simulated and real data to show their efficiency.
Tasks
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06480v1
PDF	http://arxiv.org/pdf/1609.06480v1.pdf
PWC	https://paperswithcode.com/paper/network-regularized-sparse-logistic
Repo
Framework

A Consumer BCI for Automated Music Evaluation Within a Popular On-Demand Music Streaming Service - Taking Listener’s Brainwaves to Extremes


Title	A Consumer BCI for Automated Music Evaluation Within a Popular On-Demand Music Streaming Service - Taking Listener’s Brainwaves to Extremes
Authors	Fotis Kalaganis, Dimitrios A. Adamos, Nikos Laskaris
Abstract	We investigated the possibility of using a machine-learning scheme in conjunction with commercial wearable EEG-devices for translating listener’s subjective experience of music into scores that can be used for the automated annotation of music in popular on-demand streaming services. Based on the established -neuroscientifically sound- concepts of brainwave frequency bands, activation asymmetry index and cross-frequency-coupling (CFC), we introduce a Brain Computer Interface (BCI) system that automatically assigns a rating score to the listened song. Our research operated in two distinct stages: i) a generic feature engineering stage, in which features from signal-analytics were ranked and selected based on their ability to associate music induced perturbations in brainwaves with listener’s appraisal of music. ii) a personalization stage, during which the efficiency of ex- treme learning machines (ELMs) is exploited so as to translate the derived pat- terns into a listener’s score. Encouraging experimental results, from a pragmatic use of the system, are presented.
Tasks	EEG, Feature Engineering
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06374v2
PDF	http://arxiv.org/pdf/1609.06374v2.pdf
PWC	https://paperswithcode.com/paper/a-consumer-bci-for-automated-music-evaluation
Repo
Framework

Qualitative Judgement of Research Impact: Domain Taxonomy as a Fundamental Framework for Judgement of the Quality of Research


Title	Qualitative Judgement of Research Impact: Domain Taxonomy as a Fundamental Framework for Judgement of the Quality of Research
Authors	Fionn Murtagh, Michael Orlov, Boris Mirkin
Abstract	The appeal of metric evaluation of research impact has attracted considerable interest in recent times. Although the public at large and administrative bodies are much interested in the idea, scientists and other researchers are much more cautious, insisting that metrics are but an auxiliary instrument to the qualitative peer-based judgement. The goal of this article is to propose availing of such a well positioned construct as domain taxonomy as a tool for directly assessing the scope and quality of research. We first show how taxonomies can be used to analyse the scope and perspectives of a set of research projects or papers. Then we proceed to define a research team or researcher’s rank by those nodes in the hierarchy that have been created or significantly transformed by the results of the researcher. An experimental test of the approach in the data analysis domain is described. Although the concept of taxonomy seems rather simplistic to describe all the richness of a research domain, its changes and use can be made transparent and subject to open discussions.
Tasks
Published	2016-07-11
URL	http://arxiv.org/abs/1607.03200v2
PDF	http://arxiv.org/pdf/1607.03200v2.pdf
PWC	https://paperswithcode.com/paper/qualitative-judgement-of-research-impact
Repo
Framework

A New Approach in Persian Handwritten Letters Recognition Using Error Correcting Output Coding


Title	A New Approach in Persian Handwritten Letters Recognition Using Error Correcting Output Coding
Authors	Maziar Kazemi, Muhammad Yousefnezhad, Saber Nourian
Abstract	Classification Ensemble, which uses the weighed polling of outputs, is the art of combining a set of basic classifiers for generating high-performance, robust and more stable results. This study aims to improve the results of identifying the Persian handwritten letters using Error Correcting Output Coding (ECOC) ensemble method. Furthermore, the feature selection is used to reduce the costs of errors in our proposed method. ECOC is a method for decomposing a multi-way classification problem into many binary classification tasks; and then combining the results of the subtasks into a hypothesized solution to the original problem. Firstly, the image features are extracted by Principal Components Analysis (PCA). After that, ECOC is used for identification the Persian handwritten letters which it uses Support Vector Machine (SVM) as the base classifier. The empirical results of applying this ensemble method using 10 real-world data sets of Persian handwritten letters indicate that this method has better results in identifying the Persian handwritten letters than other ensemble methods and also single classifications. Moreover, by testing a number of different features, this paper found that we can reduce the additional cost in feature selection stage by using this method.
Tasks	Feature Selection
Published	2016-04-26
URL	http://arxiv.org/abs/1604.07554v1
PDF	http://arxiv.org/pdf/1604.07554v1.pdf
PWC	https://paperswithcode.com/paper/a-new-approach-in-persian-handwritten-letters
Repo
Framework

Predicting Human Intentions from Motion Only: A 2D+3D Fusion Approach


Title	Predicting Human Intentions from Motion Only: A 2D+3D Fusion Approach
Authors	Andrea Zunino, Jacopo Cavazza, Atesh Koul, Andrea Cavallo, Cristina Becchio, Vittorio Murino
Abstract	In this paper, we address the new problem of the prediction of human intents. There is neuro-psychological evidence that actions performed by humans are anticipated by peculiar motor acts which are discriminant of the type of action going to be performed afterwards. In other words, an actual intent can be forecast by looking at the kinematics of the immediately preceding movement. To prove it in a computational and quantitative manner, we devise a new experimental setup where, without using contextual information, we predict human intents all originating from the same motor act. We posit the problem as a classification task and we introduce a new multi-modal dataset consisting of a set of motion capture marker 3D data and 2D video sequences, where, by only analysing very similar movements in both training and test phases, we are able to predict the underlying intent, i.e., the future, never observed action. We also present an extensive experimental evaluation as a baseline, customizing state-of-the-art techniques for either 3D and 2D data analysis. Realizing that video processing methods lead to inferior performance but show complementary information with respect to 3D data sequences, we developed a 2D+3D fusion analysis where we achieve better classification accuracies, attesting the superiority of the multimodal approach for the context-free prediction of human intents.
Tasks	Motion Capture
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09526v4
PDF	http://arxiv.org/pdf/1605.09526v4.pdf
PWC	https://paperswithcode.com/paper/predicting-human-intentions-from-motion-only
Repo
Framework

Solving Marginal MAP Problems with NP Oracles and Parity Constraints


Title	Solving Marginal MAP Problems with NP Oracles and Parity Constraints
Authors	Yexiang Xue, Zhiyuan Li, Stefano Ermon, Carla P. Gomes, Bart Selman
Abstract	Arising from many applications at the intersection of decision making and machine learning, Marginal Maximum A Posteriori (Marginal MAP) Problems unify the two main classes of inference, namely maximization (optimization) and marginal inference (counting), and are believed to have higher complexity than both of them. We propose XOR_MMAP, a novel approach to solve the Marginal MAP Problem, which represents the intractable counting subproblem with queries to NP oracles, subject to additional parity constraints. XOR_MMAP provides a constant factor approximation to the Marginal MAP Problem, by encoding it as a single optimization in polynomial size of the original problem. We evaluate our approach in several machine learning and decision making applications, and show that our approach outperforms several state-of-the-art Marginal MAP solvers.
Tasks	Decision Making
Published	2016-10-08
URL	http://arxiv.org/abs/1610.02591v2
PDF	http://arxiv.org/pdf/1610.02591v2.pdf
PWC	https://paperswithcode.com/paper/solving-marginal-map-problems-with-np-oracles
Repo
Framework

Deep Learning in Bioinformatics


Title	Deep Learning in Bioinformatics
Authors	Seonwoo Min, Byunghan Lee, Sungroh Yoon
Abstract	In the era of big data, transformation of biomedical big data into valuable knowledge has been one of the most important challenges in bioinformatics. Deep learning has advanced rapidly since the early 2000s and now demonstrates state-of-the-art performance in various fields. Accordingly, application of deep learning in bioinformatics to gain insight from data has been emphasized in both academia and industry. Here, we review deep learning in bioinformatics, presenting examples of current research. To provide a useful and comprehensive perspective, we categorize research both by the bioinformatics domain (i.e., omics, biomedical imaging, biomedical signal processing) and deep learning architecture (i.e., deep neural networks, convolutional neural networks, recurrent neural networks, emergent architectures) and present brief descriptions of each study. Additionally, we discuss theoretical and practical issues of deep learning in bioinformatics and suggest future research directions. We believe that this review will provide valuable insights and serve as a starting point for researchers to apply deep learning approaches in their bioinformatics studies.
Tasks
Published	2016-03-21
URL	http://arxiv.org/abs/1603.06430v5
PDF	http://arxiv.org/pdf/1603.06430v5.pdf
PWC	https://paperswithcode.com/paper/deep-learning-in-bioinformatics
Repo
Framework

Fuzzy Clustering Based Segmentation Of Vertebrae in T1-Weighted Spinal MR Images


Title	Fuzzy Clustering Based Segmentation Of Vertebrae in T1-Weighted Spinal MR Images
Authors	Jiyo. S. Athertya, G. Saravana Kumar
Abstract	Image segmentation in the medical domain is a challenging field owing to poor resolution and limited contrast. The predominantly used conventional segmentation techniques and the thresholding methods suffer from limitations because of heavy dependence on user interactions. Uncertainties prevalent in an image cannot be captured by these techniques. The performance further deteriorates when the images are corrupted by noise, outliers and other artifacts. The objective of this paper is to develop an effective robust fuzzy C- means clustering for segmenting vertebral body from magnetic resonance image owing to its unsupervised form of learning. The motivation for this work is detection of spine geometry and proper localisation and labelling will enhance the diagnostic output of a physician. The method is compared with Otsu thresholding and K-means clustering to illustrate the robustness.The reference standard for validation was the annotated images from the radiologist, and the Dice coefficient and Hausdorff distance measures were used to evaluate the segmentation.
Tasks	Semantic Segmentation
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02460v1
PDF	http://arxiv.org/pdf/1605.02460v1.pdf
PWC	https://paperswithcode.com/paper/fuzzy-clustering-based-segmentation-of
Repo
Framework

A Tutorial on Distributed (Non-Bayesian) Learning: Problem, Algorithms and Results


Title	A Tutorial on Distributed (Non-Bayesian) Learning: Problem, Algorithms and Results
Authors	Angelia Nedić, Alex Olshevsky, César A. Uribe
Abstract	We overview some results on distributed learning with focus on a family of recently proposed algorithms known as non-Bayesian social learning. We consider different approaches to the distributed learning problem and its algorithmic solutions for the case of finitely many hypotheses. The original centralized problem is discussed at first, and then followed by a generalization to the distributed setting. The results on convergence and convergence rate are presented for both asymptotic and finite time regimes. Various extensions are discussed such as those dealing with directed time-varying networks, Nesterov’s acceleration technique and a continuum sets of hypothesis.
Tasks
Published	2016-09-23
URL	http://arxiv.org/abs/1609.07537v1
PDF	http://arxiv.org/pdf/1609.07537v1.pdf
PWC	https://paperswithcode.com/paper/a-tutorial-on-distributed-non-bayesian
Repo
Framework