May 6, 2019

2440 words 12 mins read

Paper Group ANR 319

Moving Toward High Precision Dynamical Modelling in Hidden Markov Models. Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling. Fractional Order AGC for Distributed Energy Resources Using Robust Optimization. Latent Dependency Forest Models. Understanding Non-optical Remote-sensed Images: Needs, C …

Moving Toward High Precision Dynamical Modelling in Hidden Markov Models


Title	Moving Toward High Precision Dynamical Modelling in Hidden Markov Models
Authors	Sébastien Gagnon, Jean Rouat
Abstract	Hidden Markov Model (HMM) is often regarded as the dynamical model of choice in many fields and applications. It is also at the heart of most state-of-the-art speech recognition systems since the 70’s. However, from Gaussian mixture models HMMs (GMM-HMM) to deep neural network HMMs (DNN-HMM), the underlying Markovian chain of state-of-the-art models did not changed much. The “left-to-right” topology is mostly always employed because very few other alternatives exist. In this paper, we propose that finely-tuned HMM topologies are essential for precise temporal modelling and that this approach should be investigated in state-of-the-art HMM system. As such, we propose a proof-of-concept framework for learning efficient topologies by pruning down complex generic models. Speech recognition experiments that were conducted indicate that complex time dependencies can be better learned by this approach than with classical “left-to-right” models.
Tasks	Speech Recognition
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00359v1
PDF	http://arxiv.org/pdf/1607.00359v1.pdf
PWC	https://paperswithcode.com/paper/moving-toward-high-precision-dynamical
Repo
Framework

Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling


Title	Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling
Authors	Byungsoo Kim, Hwanjo Yu, Gary Geunbae Lee
Abstract	Previous studies in Open Information Extraction (Open IE) are mainly based on extraction patterns. They manually define patterns or automatically learn them from a large corpus. However, these approaches are limited when grasping the context of a sentence, and they fail to capture implicit relations. In this paper, we address this problem with the following methods. First, we exploit long short-term memory (LSTM) networks to extract higher-level features along the shortest dependency paths, connecting headwords of relations and arguments. The path-level features from LSTM networks provide useful clues regarding contextual information and the validity of arguments. Second, we constructed samples to train LSTM networks without the need for manual labeling. In particular, feedback negative sampling picks highly negative samples among non-positive samples through a model trained with positive samples. The experimental results show that our approach produces more precise and abundant extractions than state-of-the-art open IE systems. To the best of our knowledge, this is the first work to apply deep learning to Open IE.
Tasks	Open Information Extraction
Published	2016-05-25
URL	http://arxiv.org/abs/1605.07918v1
PDF	http://arxiv.org/pdf/1605.07918v1.pdf
PWC	https://paperswithcode.com/paper/automatic-open-knowledge-acquisition-via-long
Repo
Framework

Fractional Order AGC for Distributed Energy Resources Using Robust Optimization


Title	Fractional Order AGC for Distributed Energy Resources Using Robust Optimization
Authors	Indranil Pan, Saptarshi Das
Abstract	The applicability of fractional order (FO) automatic generation control (AGC) for power system frequency oscillation damping is investigated in this paper, employing distributed energy generation. The hybrid power system employs various autonomous generation systems like wind turbine, solar photovoltaic, diesel engine, fuel-cell and aqua electrolyzer along with other energy storage devices like the battery and flywheel. The controller is placed in a remote location while receiving and sending signals over an unreliable communication network with stochastic delay. The controller parameters are tuned using robust optimization techniques employing different variants of Particle Swarm Optimization (PSO) and are compared with the corresponding optimal solutions. An archival based strategy is used for reducing the number of function evaluations for the robust optimization methods. The solutions obtained through the robust optimization are able to handle higher variation in the controller gains and orders without significant decrease in the system performance. This is desirable from the FO controller implementation point of view, as the design is able to accommodate variations in the system parameter which may result due to the approximation of FO operators, using different realization methods and order of accuracy. Also a comparison is made between the FO and the integer order (IO) controllers to highlight the merits and demerits of each scheme.
Tasks
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09755v1
PDF	http://arxiv.org/pdf/1611.09755v1.pdf
PWC	https://paperswithcode.com/paper/fractional-order-agc-for-distributed-energy
Repo
Framework

Latent Dependency Forest Models


Title	Latent Dependency Forest Models
Authors	Shanbo Chu, Yong Jiang, Kewei Tu
Abstract	Probabilistic modeling is one of the foundations of modern machine learning and artificial intelligence. In this paper, we propose a novel type of probabilistic models named latent dependency forest models (LDFMs). A LDFM models the dependencies between random variables with a forest structure that can change dynamically based on the variable values. It is therefore capable of modeling context-specific independence. We parameterize a LDFM using a first-order non-projective dependency grammar. Learning LDFMs from data can be formulated purely as a parameter learning problem, and hence the difficult problem of model structure learning is circumvented. Our experimental results show that LDFMs are competitive with existing probabilistic models.
Tasks
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02236v2
PDF	http://arxiv.org/pdf/1609.02236v2.pdf
PWC	https://paperswithcode.com/paper/latent-dependency-forest-models
Repo
Framework

Understanding Non-optical Remote-sensed Images: Needs, Challenges and Ways Forward


Title	Understanding Non-optical Remote-sensed Images: Needs, Challenges and Ways Forward
Authors	Amit Kumar Mishra
Abstract	Non-optical remote-sensed images are going to be used more often in man- aging disaster, crime and precision agriculture. With more small satellites and unmanned air vehicles planning to carry radar and hyperspectral image sensors there is going to be an abundance of such data in the recent future. Understanding these data in real-time will be crucial in attaining some of the important sustain- able development goals. Processing non-optical images is, in many ways, different from that of optical images. Most of the recent advances in the domain of image understanding has been using optical images. In this article we shall explain the needs for image understanding in non-optical domain and the typical challenges. Then we shall describe the existing approaches and how we can move from there to the desired goal of a reliable real-time image understanding system.
Tasks
Published	2016-12-23
URL	http://arxiv.org/abs/1612.07921v1
PDF	http://arxiv.org/pdf/1612.07921v1.pdf
PWC	https://paperswithcode.com/paper/understanding-non-optical-remote-sensed
Repo
Framework

Liftago On-Demand Transport Dataset and Market Formation Algorithm Based on Machine Learning


Title	Liftago On-Demand Transport Dataset and Market Formation Algorithm Based on Machine Learning
Authors	Jan Mrkos, Jan Drchal, Malcolm Egan, Michal Jakob
Abstract	This document serves as a technical report for the analysis of on-demand transport dataset. Moreover we show how the dataset can be used to develop a market formation algorithm based on machine learning. Data used in this work comes from Liftago, a Prague based company which connects taxi drivers and customers through a smartphone app. The dataset is analysed from the machine-learning perspective: we give an overview of features available as well as results of feature ranking. Later we propose the SImple Data-driven MArket Formation (SIDMAF) algorithm which aims to improve a relevance while connecting customers with relevant drivers. We compare the heuristics currently used by Liftago with SIDMAF using two key performance indicators.
Tasks
Published	2016-08-09
URL	http://arxiv.org/abs/1608.02858v1
PDF	http://arxiv.org/pdf/1608.02858v1.pdf
PWC	https://paperswithcode.com/paper/liftago-on-demand-transport-dataset-and
Repo
Framework

An Analysis of General Fuzzy Logic and Fuzzy Reasoning Method


Title	An Analysis of General Fuzzy Logic and Fuzzy Reasoning Method
Authors	Kwak Son Il
Abstract	In this article, we describe the fuzzy logic, fuzzy language and algorithms as the basis of fuzzy reasoning, one of the intelligent information processing method, and then describe the general fuzzy reasoning method.
Tasks
Published	2016-04-07
URL	http://arxiv.org/abs/1604.03210v1
PDF	http://arxiv.org/pdf/1604.03210v1.pdf
PWC	https://paperswithcode.com/paper/an-analysis-of-general-fuzzy-logic-and-fuzzy
Repo
Framework

Detecting Violent and Abnormal Crowd activity using Temporal Analysis of Grey Level Co-occurrence Matrix (GLCM) Based Texture Measures


Title	Detecting Violent and Abnormal Crowd activity using Temporal Analysis of Grey Level Co-occurrence Matrix (GLCM) Based Texture Measures
Authors	Kaelon Lloyd, David Marshall, Simon C. Moore, Paul L. Rosin
Abstract	The severity of sustained injury resulting from assault-related violence can be minimised by reducing detection time. However, it has been shown that human operators perform poorly at detecting events found in video footage when presented with simultaneous feeds. We utilise computer vision techniques to develop an automated method of abnormal crowd detection that can aid a human operator in the detection of violent behaviour. We observed that behaviour in city centre environments often occur in crowded areas, resulting in individual actions being occluded by other crowd members. We propose a real-time descriptor that models crowd dynamics by encoding changes in crowd texture using temporal summaries of Grey Level Co-Occurrence Matrix (GLCM) features. We introduce a measure of inter-frame uniformity (IFU) and demonstrate that the appearance of violent behaviour changes in a less uniform manner when compared to other types of crowd behaviour. Our proposed method is computationally cheap and offers real-time description. Evaluating our method using a privately held CCTV dataset and the publicly available Violent Flows, UCF Web Abnormality, and UMN Abnormal Crowd datasets, we report a receiver operating characteristic score of 0.9782, 0.9403, 0.8218 and 0.9956 respectively.
Tasks
Published	2016-05-17
URL	http://arxiv.org/abs/1605.05106v2
PDF	http://arxiv.org/pdf/1605.05106v2.pdf
PWC	https://paperswithcode.com/paper/detecting-violent-and-abnormal-crowd-activity
Repo
Framework

Efficient Pose and Cell Segmentation using Column Generation


Title	Efficient Pose and Cell Segmentation using Column Generation
Authors	Shaofei Wang, Chong Zhang, Miguel A. Gonzalez-Ballester, Julian Yarkony
Abstract	We study the problems of multi-person pose segmentation in natural images and instance segmentation in biological images with crowded cells. We formulate these distinct tasks as integer programs where variables correspond to poses/cells. To optimize, we propose a generic relaxation scheme for solving these combinatorial problems using a column generation formulation where the program for generating a column is solved via exact optimization of very small scale integer programs. This results in efficient exploration of the spaces of poses and cells.
Tasks	Cell Segmentation, Efficient Exploration, Instance Segmentation, Semantic Segmentation
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00437v1
PDF	http://arxiv.org/pdf/1612.00437v1.pdf
PWC	https://paperswithcode.com/paper/efficient-pose-and-cell-segmentation-using
Repo
Framework

Global Vertices and the Noising Paradox


Title	Global Vertices and the Noising Paradox
Authors	Konstantinos A. Raftopoulos, Stefanos D. Kollias, Marin Ferecatu
Abstract	A theoretical and experimental analysis related to the identification of vertices of unknown shapes is presented. Shapes are seen as real functions of their closed boundary. Unlike traditional approaches, which see curvature as the rate of change of the tangent to the curve, an alternative global perspective of curvature is examined providing insight into the process of noise-enabled vertex localization. The analysis leads to a paradox, that certain vertices can be localized better in the presence of noise. The concept of noising is thus considered and a relevant global method for localizing “Global Vertices” is investigated. Theoretical analysis reveals that induced noise can help localizing certain vertices if combined with global descriptors. Experiments with noise and a comparison to localized methods validate the theoretical results.
Tasks
Published	2016-08-02
URL	http://arxiv.org/abs/1608.00668v1
PDF	http://arxiv.org/pdf/1608.00668v1.pdf
PWC	https://paperswithcode.com/paper/global-vertices-and-the-noising-paradox
Repo
Framework

Modeling documents with Generative Adversarial Networks


Title	Modeling documents with Generative Adversarial Networks
Authors	John Glover
Abstract	This paper describes a method for using Generative Adversarial Networks to learn distributed representations of natural language documents. We propose a model that is based on the recently proposed Energy-Based GAN, but instead uses a Denoising Autoencoder as the discriminator network. Document representations are extracted from the hidden layer of the discriminator and evaluated both quantitatively and qualitatively.
Tasks	Denoising
Published	2016-12-29
URL	http://arxiv.org/abs/1612.09122v1
PDF	http://arxiv.org/pdf/1612.09122v1.pdf
PWC	https://paperswithcode.com/paper/modeling-documents-with-generative
Repo
Framework

Hands-Free Segmentation of Medical Volumes via Binary Inputs


Title	Hands-Free Segmentation of Medical Volumes via Binary Inputs
Authors	Florian Dubost, Loic Peter, Christian Rupprecht, Benjamin Gutierrez-Becker, Nassir Navab
Abstract	We propose a novel hands-free method to interactively segment 3D medical volumes. In our scenario, a human user progressively segments an organ by answering a series of questions of the form “Is this voxel inside the object to segment?". At each iteration, the chosen question is defined as the one halving a set of candidate segmentations given the answered questions. For a quick and efficient exploration, these segmentations are sampled according to the Metropolis-Hastings algorithm. Our sampling technique relies on a combination of relaxed shape prior, learnt probability map and consistency with previous answers. We demonstrate the potential of our strategy on a prostate segmentation MRI dataset. Through the study of failure cases with synthetic examples, we demonstrate the adaptation potential of our method. We also show that our method outperforms two intuitive baselines: one based on random questions, the other one being the thresholded probability map.
Tasks	Efficient Exploration
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06192v1
PDF	http://arxiv.org/pdf/1609.06192v1.pdf
PWC	https://paperswithcode.com/paper/hands-free-segmentation-of-medical-volumes
Repo
Framework

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems


Title	BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
Authors	Zachary C. Lipton, Xiujun Li, Jianfeng Gao, Lihong Li, Faisal Ahmed, Li Deng
Abstract	We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $\epsilon$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.
Tasks	Efficient Exploration, Q-Learning, Task-Oriented Dialogue Systems
Published	2016-08-17
URL	http://arxiv.org/abs/1608.05081v4
PDF	http://arxiv.org/pdf/1608.05081v4.pdf
PWC	https://paperswithcode.com/paper/bbq-networks-efficient-exploration-in-deep-1
Repo
Framework

Angrier Birds: Bayesian reinforcement learning


Title	Angrier Birds: Bayesian reinforcement learning
Authors	Imanol Arrieta Ibarra, Bernardo Ramos, Lars Roemheld
Abstract	We train a reinforcement learner to play a simplified version of the game Angry Birds. The learner is provided with a game state in a manner similar to the output that could be produced by computer vision algorithms. We improve on the efficiency of regular {\epsilon}-greedy Q-Learning with linear function approximation through more systematic exploration in Randomized Least Squares Value Iteration (RLSVI), an algorithm that samples its policy from a posterior distribution on optimal policies. With larger state-action spaces, efficient exploration becomes increasingly important, as evidenced by the faster learning in RLSVI.
Tasks	Efficient Exploration, Q-Learning
Published	2016-01-06
URL	http://arxiv.org/abs/1601.01297v2
PDF	http://arxiv.org/pdf/1601.01297v2.pdf
PWC	https://paperswithcode.com/paper/angrier-birds-bayesian-reinforcement-learning
Repo
Framework

Variance-Reduced and Projection-Free Stochastic Optimization


Title	Variance-Reduced and Projection-Free Stochastic Optimization
Authors	Elad Hazan, Haipeng Luo
Abstract	The Frank-Wolfe optimization algorithm has recently regained popularity for machine learning applications due to its projection-free property and its ability to handle structured constraints. However, in the stochastic learning setting, it is still relatively understudied compared to the gradient descent counterpart. In this work, leveraging a recent variance reduction technique, we propose two stochastic Frank-Wolfe variants which substantially improve previous results in terms of the number of stochastic gradient evaluations needed to achieve $1-\epsilon$ accuracy. For example, we improve from $O(\frac{1}{\epsilon})$ to $O(\ln\frac{1}{\epsilon})$ if the objective function is smooth and strongly convex, and from $O(\frac{1}{\epsilon^2})$ to $O(\frac{1}{\epsilon^{1.5}})$ if the objective function is smooth and Lipschitz. The theoretical improvement is also observed in experiments on real-world datasets for a multiclass classification application.
Tasks	Stochastic Optimization
Published	2016-02-05
URL	http://arxiv.org/abs/1602.02101v2
PDF	http://arxiv.org/pdf/1602.02101v2.pdf
PWC	https://paperswithcode.com/paper/variance-reduced-and-projection-free
Repo
Framework