May 7, 2019

2827 words 14 mins read

Paper Group ANR 139

WASSUP? LOL : Characterizing Out-of-Vocabulary Words in Twitter. Image Classification of Grapevine Buds using Scale-Invariant Features Transform, Bag of Features and Support Vector Machines. Information Theoretically Aided Reinforcement Learning for Embodied Agents. A Probabilistic Machine Learning Approach to Detect Industrial Plant Faults. Study …

WASSUP? LOL : Characterizing Out-of-Vocabulary Words in Twitter


Title	WASSUP? LOL : Characterizing Out-of-Vocabulary Words in Twitter
Authors	Suman Kalyan Maity, Chaitanya Sarda, Anshit Chaudhary, Abhijeet Patil, Shraman Kumar, Akash Mondal, Animesh Mukherjee
Abstract	Language in social media is mostly driven by new words and spellings that are constantly entering the lexicon thereby polluting it and resulting in high deviation from the formal written version. The primary entities of such language are the out-of-vocabulary (OOV) words. In this paper, we study various sociolinguistic properties of the OOV words and propose a classification model to categorize them into at least six categories. We achieve 81.26% accuracy with high precision and recall. We observe that the content features are the most discriminative ones followed by lexical and context features.
Tasks
Published	2016-01-31
URL	http://arxiv.org/abs/1602.00293v1
PDF	http://arxiv.org/pdf/1602.00293v1.pdf
PWC	https://paperswithcode.com/paper/wassup-lol-characterizing-out-of-vocabulary
Repo
Framework

Image Classification of Grapevine Buds using Scale-Invariant Features Transform, Bag of Features and Support Vector Machines


Title	Image Classification of Grapevine Buds using Scale-Invariant Features Transform, Bag of Features and Support Vector Machines
Authors	Diego Sebastián Pérez, Facundo Bromberg, Carlos Ariel Diaz
Abstract	In viticulture, there are several applications where bud detection in vineyard images is a necessary task, susceptible of being automated through the use of computer vision methods. A common and effective family of visual detection algorithms are the scanning-window type, that slide a (usually) fixed size window along the original image, classifying each resulting windowed-patch as containing or not containing the target object. The simplicity of these algorithms finds its most challenging aspect in the classification stage. Interested in grapevine buds detection in natural field conditions, this paper presents a classification method for images of grapevine buds ranging 100 to 1600 pixels in diameter, captured in outdoor, under natural field conditions, in winter (i.e., no grape bunches, very few leaves, and dormant buds), without artificial background, and with minimum equipment requirements. The proposed method uses well-known computer vision technologies: Scale-Invariant Feature Transform for calculating low-level features, Bag of Features for building an image descriptor, and Support Vector Machines for training a classifier. When evaluated over images containing buds of at least 100 pixels in diameter, the approach achieves a recall higher than 0.9 and a precision of 0.86 over all windowed-patches covering the whole bud and down to 60% of it, and scaled up to window patches containing a proportion of 20%-80% of bud versus background pixels. This robustness on the position and size of the window demonstrates its viability for use as the classification stage in a scanning-window detection algorithms.
Tasks	Image Classification, Window Detection
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02775v1
PDF	http://arxiv.org/pdf/1605.02775v1.pdf
PWC	https://paperswithcode.com/paper/image-classification-of-grapevine-buds-using
Repo
Framework

Information Theoretically Aided Reinforcement Learning for Embodied Agents


Title	Information Theoretically Aided Reinforcement Learning for Embodied Agents
Authors	Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay
Abstract	Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landscape while preserving the global optimizers of interest. We show that policy gradient optimization for locomotion in a complex morphology is significantly improved when supplementing the extrinsic reward by an intrinsic reward defined in terms of the mutual information of time consecutive sensor readings.
Tasks
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09735v1
PDF	http://arxiv.org/pdf/1605.09735v1.pdf
PWC	https://paperswithcode.com/paper/information-theoretically-aided-reinforcement
Repo
Framework

A Probabilistic Machine Learning Approach to Detect Industrial Plant Faults


Title	A Probabilistic Machine Learning Approach to Detect Industrial Plant Faults
Authors	Wei Xiao
Abstract	Fault detection in industrial plants is a hot research area as more and more sensor data are being collected throughout the industrial process. Automatic data-driven approaches are widely needed and seen as a promising area of investment. This paper proposes an effective machine learning algorithm to predict industrial plant faults based on classification methods such as penalized logistic regression, random forest and gradient boosted tree. A fault’s start time and end time are predicted sequentially in two steps by formulating the original prediction problems as classification problems. The algorithms described in this paper won first place in the Prognostics and Health Management Society 2015 Data Challenge.
Tasks	Fault Detection
Published	2016-03-18
URL	http://arxiv.org/abs/1603.05770v1
PDF	http://arxiv.org/pdf/1603.05770v1.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-machine-learning-approach-to
Repo
Framework

Study on Feature Subspace of Archetypal Emotions for Speech Emotion Recognition


Title	Study on Feature Subspace of Archetypal Emotions for Speech Emotion Recognition
Authors	Xi Ma, Zhiyong Wu, Jia Jia, Mingxing Xu, Helen Meng, Lianhong Cai
Abstract	Feature subspace selection is an important part in speech emotion recognition. Most of the studies are devoted to finding a feature subspace for representing all emotions. However, some studies have indicated that the features associated with different emotions are not exactly the same. Hence, traditional methods may fail to distinguish some of the emotions with just one global feature subspace. In this work, we propose a new divide and conquer idea to solve the problem. First, the feature subspaces are constructed for all the combinations of every two different emotions (emotion-pair). Bi-classifiers are then trained on these feature subspaces respectively. The final emotion recognition result is derived by the voting and competition method. Experimental results demonstrate that the proposed method can get better results than the traditional multi-classification method.
Tasks	Emotion Recognition, Speech Emotion Recognition
Published	2016-11-17
URL	http://arxiv.org/abs/1611.05675v1
PDF	http://arxiv.org/pdf/1611.05675v1.pdf
PWC	https://paperswithcode.com/paper/study-on-feature-subspace-of-archetypal
Repo
Framework

A Bayesian Approach to the Data Description Problem


Title	A Bayesian Approach to the Data Description Problem
Authors	Alireza Ghasemi, Hamid R. Rabiee, Mohammad T. Manzuri, M. H. Rohban
Abstract	In this paper, we address the problem of data description using a Bayesian framework. The goal of data description is to draw a boundary around objects of a certain class of interest to discriminate that class from the rest of the feature space. Data description is also known as one-class learning and has a wide range of applications. The proposed approach uses a Bayesian framework to precisely compute the class boundary and therefore can utilize domain information in form of prior knowledge in the framework. It can also operate in the kernel space and therefore recognize arbitrary boundary shapes. Moreover, the proposed method can utilize unlabeled data in order to improve accuracy of discrimination. We evaluate our method using various real-world datasets and compare it with other state of the art approaches of data description. Experiments show promising results and improved performance over other data description and one-class learning algorithms.
Tasks
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07507v1
PDF	http://arxiv.org/pdf/1602.07507v1.pdf
PWC	https://paperswithcode.com/paper/a-bayesian-approach-to-the-data-description
Repo
Framework

Learning overcomplete, low coherence dictionaries with linear inference


Title	Learning overcomplete, low coherence dictionaries with linear inference
Authors	Jesse A. Livezey, Alejandro F. Bujan, Friedrich T. Sommer
Abstract	Finding overcomplete latent representations of data has applications in data analysis, signal processing, machine learning, theoretical neuroscience and many other fields. In an overcomplete representation, the number of latent features exceeds the data dimensionality, which is useful when the data is undersampled by the measurements (compressed sensing, information bottlenecks in neural systems) or composed from multiple complete sets of linear features, each spanning the data space. Independent Components Analysis (ICA) is a linear technique for learning sparse latent representations, which typically has a lower computational cost than sparse coding, its nonlinear, recurrent counterpart. While well suited for finding complete representations, we show that overcompleteness poses a challenge to existing ICA algorithms. Specifically, the coherence control in existing ICA algorithms, necessary to prevent the formation of duplicate dictionary features, is ill-suited in the overcomplete case. We show that in this case several existing ICA algorithms have undesirable global minima that maximize coherence. Further, by comparing ICA algorithms on synthetic data and natural images to the computationally more expensive sparse coding solution, we show that the coherence control biases the exploration of the data manifold, sometimes yielding suboptimal solutions. We provide a theoretical explanation of these failures and, based on the theory, propose improved overcomplete ICA algorithms. All told, this study contributes new insights into and methods for coherence control for linear ICA, some of which are applicable to many other, potentially nonlinear, unsupervised learning methods.
Tasks
Published	2016-06-10
URL	http://arxiv.org/abs/1606.03474v4
PDF	http://arxiv.org/pdf/1606.03474v4.pdf
PWC	https://paperswithcode.com/paper/learning-overcomplete-low-coherence
Repo
Framework

SentiBubbles: Topic Modeling and Sentiment Visualization of Entity-centric Tweets


Title	SentiBubbles: Topic Modeling and Sentiment Visualization of Entity-centric Tweets
Authors	João Oliveira, Mike Pinto, Pedro Saleiro, Jorge Teixeira
Abstract	Social Media users tend to mention entities when reacting to news events. The main purpose of this work is to create entity-centric aggregations of tweets on a daily basis. By applying topic modeling and sentiment analysis, we create data visualization insights about current events and people reactions to those events from an entity-centric perspective.
Tasks	Sentiment Analysis
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00167v2
PDF	http://arxiv.org/pdf/1607.00167v2.pdf
PWC	https://paperswithcode.com/paper/sentibubbles-topic-modeling-and-sentiment
Repo
Framework

An interactive fuzzy goal programming algorithm to solve decentralized bi-level multiobjective fractional programming problem


Title	An interactive fuzzy goal programming algorithm to solve decentralized bi-level multiobjective fractional programming problem
Authors	Hasan Dalman
Abstract	This paper proposes a fuzzy goal programming based on Taylor series for solving decentralized bi-level multiobjective fractional programming (DBLMOFP) problem. In the proposed approach, all of the membership functions are associated with the fuzzy goals of each objective at the both levels and also the fractional membership functions are converted to linear functions using the Taylor series approach. Then a fuzzy goal programming is proposed to reach the highest degree of each of the membership goals by taking the most satisfactory solution for all decision makers at the both levels. Finally, a numerical example is presented to illustrate the effectiveness of the proposed approach.
Tasks
Published	2016-06-02
URL	http://arxiv.org/abs/1606.00927v1
PDF	http://arxiv.org/pdf/1606.00927v1.pdf
PWC	https://paperswithcode.com/paper/an-interactive-fuzzy-goal-programming
Repo
Framework

Online Action Detection


Title	Online Action Detection
Authors	Roeland De Geest, Efstratios Gavves, Amir Ghodrati, Zhenyang Li, Cees Snoek, Tinne Tuytelaars
Abstract	In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This is a very challenging problem for four reasons. First, only partial actions are observed. Second, there is a large variability in negative data. Third, the start of the action is unknown, so it is unclear over what time window the information should be integrated. Finally, in real world data, large within-class variability exists. This problem has been addressed before, but only to some extent. Our contributions to online action detection are threefold. First, we introduce a realistic dataset composed of 27 episodes from 6 popular TV series. The dataset spans over 16 hours of footage annotated with 30 action classes, totaling 6,231 action instances. Second, we analyze and compare various baseline methods, showing this is a challenging problem for which none of the methods provides a good solution. Third, we analyze the change in performance when there is a variation in viewpoint, occlusion, truncation, etc. We introduce an evaluation protocol for fair comparison. The dataset, the baselines and the models will all be made publicly available to encourage (much needed) further research on online action detection on realistic data.
Tasks	Action Detection
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06506v2
PDF	http://arxiv.org/pdf/1604.06506v2.pdf
PWC	https://paperswithcode.com/paper/online-action-detection
Repo
Framework

Weighted Residuals for Very Deep Networks


Title	Weighted Residuals for Very Deep Networks
Authors	Falong Shen, Gang Zeng
Abstract	Deep residual networks have recently shown appealing performance on many challenging computer vision tasks. However, the original residual structure still has some defects making it difficult to converge on very deep networks. In this paper, we introduce a weighted residual network to address the incompatibility between \texttt{ReLU} and element-wise addition and the deep network initialization problem. The weighted residual network is able to learn to combine residuals from different layers effectively and efficiently. The proposed models enjoy a consistent improvement over accuracy and convergence with increasing depths from 100+ layers to 1000+ layers. Besides, the weighted residual networks have little more computation and GPU memory burden than the original residual networks. The networks are optimized by projected stochastic gradient descent. Experiments on CIFAR-10 have shown that our algorithm has a \emph{faster convergence speed} than the original residual networks and reaches a \emph{high accuracy} at 95.3% with a 1192-layer model.
Tasks
Published	2016-05-28
URL	http://arxiv.org/abs/1605.08831v1
PDF	http://arxiv.org/pdf/1605.08831v1.pdf
PWC	https://paperswithcode.com/paper/weighted-residuals-for-very-deep-networks
Repo
Framework

Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation


Title	Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation
Authors	Akash Srivastava, James Zou, Ryan P. Adams, Charles Sutton
Abstract	A good clustering can help a data analyst to explore and understand a data set, but what constitutes a good clustering may depend on domain-specific and application-specific criteria. These criteria can be difficult to formalize, even when it is easy for an analyst to know a good clustering when they see one. We present a new approach to interactive clustering for data exploration called TINDER, based on a particularly simple feedback mechanism, in which an analyst can reject a given clustering and request a new one, which is chosen to be different from the previous clustering while fitting the data well. We formalize this interaction in a Bayesian framework as a method for prior elicitation, in which each different clustering is produced by a prior distribution that is modified to discourage previously rejected clusterings. We show that TINDER successfully produces a diverse set of clusterings, each of equivalent quality, that are much more diverse than would be obtained by randomized restarts.
Tasks
Published	2016-06-19
URL	http://arxiv.org/abs/1606.05896v1
PDF	http://arxiv.org/pdf/1606.05896v1.pdf
PWC	https://paperswithcode.com/paper/clustering-with-a-reject-option-interactive
Repo
Framework

Merging MCMC Subposteriors through Gaussian-Process Approximations


Title	Merging MCMC Subposteriors through Gaussian-Process Approximations
Authors	Christopher Nemeth, Chris Sherlock
Abstract	Markov chain Monte Carlo (MCMC) algorithms have become powerful tools for Bayesian inference. However, they do not scale well to large-data problems. Divide-and-conquer strategies, which split the data into batches and, for each batch, run independent MCMC algorithms targeting the corresponding subposterior, can spread the computational burden across a number of separate workers. The challenge with such strategies is in recombining the subposteriors to approximate the full posterior. By creating a Gaussian-process approximation for each log-subposterior density we create a tractable approximation for the full posterior. This approximation is exploited through three methodologies: firstly a Hamiltonian Monte Carlo algorithm targeting the expectation of the posterior density provides a sample from an approximation to the posterior; secondly, evaluating the true posterior at the sampled points leads to an importance sampler that, asymptotically, targets the true posterior expectations; finally, an alternative importance sampler uses the full Gaussian-process distribution of the approximation to the log-posterior density to re-weight any initial sample and provide both an estimate of the posterior expectation and a measure of the uncertainty in it.
Tasks	Bayesian Inference
Published	2016-05-27
URL	http://arxiv.org/abs/1605.08576v2
PDF	http://arxiv.org/pdf/1605.08576v2.pdf
PWC	https://paperswithcode.com/paper/merging-mcmc-subposteriors-through-gaussian
Repo
Framework

Hierarchical Decision Making In Electricity Grid Management


Title	Hierarchical Decision Making In Electricity Grid Management
Authors	Gal Dalal, Elad Gilboa, Shie Mannor
Abstract	The power grid is a complex and vital system that necessitates careful reliability management. Managing the grid is a difficult problem with multiple time scales of decision making and stochastic behavior due to renewable energy generations, variable demand and unplanned outages. Solving this problem in the face of uncertainty requires a new methodology with tractable algorithms. In this work, we introduce a new model for hierarchical decision making in complex systems. We apply reinforcement learning (RL) methods to learn a proxy, i.e., a level of abstraction, for real-time power grid reliability. We devise an algorithm that alternates between slow time-scale policy improvement, and fast time-scale value function approximation. We compare our results to prevailing heuristics, and show the strength of our method.
Tasks	Decision Making
Published	2016-03-06
URL	http://arxiv.org/abs/1603.01840v1
PDF	http://arxiv.org/pdf/1603.01840v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-decision-making-in-electricity
Repo
Framework

Revealing Fundamental Physics from the Daya Bay Neutrino Experiment using Deep Neural Networks


Title	Revealing Fundamental Physics from the Daya Bay Neutrino Experiment using Deep Neural Networks
Authors	Evan Racah, Seyoon Ko, Peter Sadowski, Wahid Bhimji, Craig Tull, Sang-Yun Oh, Pierre Baldi, Prabhat
Abstract	Experiments in particle physics produce enormous quantities of data that must be analyzed and interpreted by teams of physicists. This analysis is often exploratory, where scientists are unable to enumerate the possible types of signal prior to performing the experiment. Thus, tools for summarizing, clustering, visualizing and classifying high-dimensional data are essential. In this work, we show that meaningful physical content can be revealed by transforming the raw data into a learned high-level representation using deep neural networks, with measurements taken at the Daya Bay Neutrino Experiment as a case study. We further show how convolutional deep neural networks can provide an effective classification filter with greater than 97% accuracy across different classes of physics events, significantly better than other machine learning approaches.
Tasks
Published	2016-01-28
URL	http://arxiv.org/abs/1601.07621v3
PDF	http://arxiv.org/pdf/1601.07621v3.pdf
PWC	https://paperswithcode.com/paper/revealing-fundamental-physics-from-the-daya
Repo
Framework