July 27, 2019

3181 words 15 mins read

Paper Group ANR 564

A Tribe Competition-Based Genetic Algorithm for Feature Selection in Pattern Classification. Restoration of Images with Wavefront Aberrations. Automatic Taxonomy Generation - A Use-Case in the Legal Domain. Online Tool Condition Monitoring Based on Parsimonious Ensemble+. Exact Topology Reconstruction of Radial Dynamical Systems with Applications t …

A Tribe Competition-Based Genetic Algorithm for Feature Selection in Pattern Classification


Title	A Tribe Competition-Based Genetic Algorithm for Feature Selection in Pattern Classification
Authors	Benteng Ma, Yong Xia
Abstract	Feature selection has always been a critical step in pattern recognition, in which evolutionary algorithms, such as the genetic algorithm (GA), are most commonly used. However, the individual encoding scheme used in various GAs would either pose a bias on the solution or require a pre-specified number of features, and hence may lead to less accurate results. In this paper, a tribe competition-based genetic algorithm (TCbGA) is proposed for feature selection in pattern classification. The population of individuals is divided into multiple tribes, and the initialization and evolutionary operations are modified to ensure that the number of selected features in each tribe follows a Gaussian distribution. Thus each tribe focuses on exploring a specific part of the solution space. Meanwhile, tribe competition is introduced to the evolution process, which allows the winning tribes, which produce better individuals, to enlarge their sizes, i.e. having more individuals to search their parts of the solution space. This algorithm, therefore, avoids the bias on solutions and requirement of a pre-specified number of features. We have evaluated our algorithm against several state-of-the-art feature selection approaches on 20 benchmark datasets. Our results suggest that the proposed TCbGA algorithm can identify the optimal feature subset more effectively and produce more accurate pattern classification.
Tasks	Feature Selection
Published	2017-04-28
URL	http://arxiv.org/abs/1704.08818v1
PDF	http://arxiv.org/pdf/1704.08818v1.pdf
PWC	https://paperswithcode.com/paper/a-tribe-competition-based-genetic-algorithm
Repo
Framework

Restoration of Images with Wavefront Aberrations


Title	Restoration of Images with Wavefront Aberrations
Authors	Claudius Zelenka, Reinhard Koch
Abstract	This contribution deals with image restoration in optical systems with coherent illumination, which is an important topic in astronomy, coherent microscopy and radar imaging. Such optical systems suffer from wavefront distortions, which are caused by imperfect imaging components and conditions. Known image restoration algorithms work well for incoherent imaging, they fail in case of coherent images. In this paper a novel wavefront correction algorithm is presented, which allows image restoration under coherent conditions. In most coherent imaging systems, especially in astronomy, the wavefront deformation is known. Using this information, the proposed algorithm allows a high quality restoration even in case of severe wavefront distortions. We present two versions of this algorithm, which are an evolution of the Gerchberg-Saxton and the Hybrid-Input-Output algorithm. The algorithm is verified on simulated and real microscopic images.
Tasks	Image Restoration
Published	2017-04-02
URL	http://arxiv.org/abs/1704.00331v1
PDF	http://arxiv.org/pdf/1704.00331v1.pdf
PWC	https://paperswithcode.com/paper/restoration-of-images-with-wavefront
Repo
Framework

Automatic Taxonomy Generation - A Use-Case in the Legal Domain


Title	Automatic Taxonomy Generation - A Use-Case in the Legal Domain
Authors	Cécile Robin, James O’Neill, Paul Buitelaar
Abstract	A key challenge in the legal domain is the adaptation and representation of the legal knowledge expressed through texts, in order for legal practitioners and researchers to access this information easier and faster to help with compliance related issues. One way to approach this goal is in the form of a taxonomy of legal concepts. While this task usually requires a manual construction of terms and their relations by domain experts, this paper describes a methodology to automatically generate a taxonomy of legal noun concepts. We apply and compare two approaches on a corpus consisting of statutory instruments for UK, Wales, Scotland and Northern Ireland laws.
Tasks
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01823v1
PDF	http://arxiv.org/pdf/1710.01823v1.pdf
PWC	https://paperswithcode.com/paper/automatic-taxonomy-generation-a-use-case-in
Repo
Framework

Online Tool Condition Monitoring Based on Parsimonious Ensemble+


Title	Online Tool Condition Monitoring Based on Parsimonious Ensemble+
Authors	Mahardhika Pratama, Eric Dimla, Edwin Lughofer, Witold Pedrycz, Tegoeh Tjahjowidowo
Abstract	Accurate diagnosis of tool wear in metal turning process remains an open challenge for both scientists and industrial practitioners because of inhomogeneities in workpiece material, nonstationary machining settings to suit production requirements, and nonlinear relations between measured variables and tool wear. Common methodologies for tool condition monitoring still rely on batch approaches which cannot cope with a fast sampling rate of metal cutting process. Furthermore they require a retraining process to be completed from scratch when dealing with a new set of machining parameters. This paper presents an online tool condition monitoring approach based on Parsimonious Ensemble+, pENsemble+. The unique feature of pENsemble+ lies in its highly flexible principle where both ensemble structure and base-classifier structure can automatically grow and shrink on the fly based on the characteristics of data streams. Moreover, the online feature selection scenario is integrated to actively sample relevant input attributes. The paper presents advancement of a newly developed ensemble learning algorithm, pENsemble+, where online active learning scenario is incorporated to reduce operator labelling effort. The ensemble merging scenario is proposed which allows reduction of ensemble complexity while retaining its diversity. Experimental studies utilising real-world manufacturing data streams and comparisons with well known algorithms were carried out. Furthermore, the efficacy of pENsemble was examined using benchmark concept drift data streams. It has been found that pENsemble+ incurs low structural complexity and results in a significant reduction of operator labelling effort.
Tasks	Active Learning, Feature Selection
Published	2017-11-06
URL	https://arxiv.org/abs/1711.01843v2
PDF	https://arxiv.org/pdf/1711.01843v2.pdf
PWC	https://paperswithcode.com/paper/online-tool-condition-monitoring-based-on
Repo
Framework

Exact Topology Reconstruction of Radial Dynamical Systems with Applications to Distribution System of the Power Grid


Title	Exact Topology Reconstruction of Radial Dynamical Systems with Applications to Distribution System of the Power Grid
Authors	Saurav Talukdar, Deepjyoti Deka, Donatello Materassi, Murti V. Salapaka
Abstract	In this article we present a method to reconstruct the interconnectedness of dynamically related stochastic processes, where the interactions are bi-directional and the underlying topology is a tree. Our approach is based on multivariate Wiener filtering which recovers spurious edges apart from the true edges in the topology reconstruction. The main contribution of this work is to show that all spurious links obtained using Wiener filtering can be eliminated if the underlying topology is a tree based on which we present a three stage network reconstruction procedure for trees. We illustrate the effectiveness of the method developed by applying it on a typical distribution system of the electric grid.
Tasks
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00847v1
PDF	http://arxiv.org/pdf/1703.00847v1.pdf
PWC	https://paperswithcode.com/paper/exact-topology-reconstruction-of-radial
Repo
Framework

A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)


Title	A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
Authors	Saber Moradi, Ning Qiao, Fabio Stefanini, Giacomo Indiveri
Abstract	Neuromorphic computing systems comprise networks of neurons that use asynchronous events for both computation and communication. This type of representation offers several advantages in terms of bandwidth and power consumption in neuromorphic electronic systems. However, managing the traffic of asynchronous events in large scale systems is a daunting task, both in terms of circuit complexity and memory requirements. Here we present a novel routing methodology that employs both hierarchical and mesh routing strategies and combines heterogeneous memory structures for minimizing both memory requirements and latency, while maximizing programming flexibility to support a wide range of event-based neural network architectures, through parameter configuration. We validated the proposed scheme in a prototype multi-core neuromorphic processor chip that employs hybrid analog/digital circuits for emulating synapse and neuron dynamics together with asynchronous digital circuits for managing the address-event traffic. We present a theoretical analysis of the proposed connectivity scheme, describe the methods and circuits used to implement such scheme, and characterize the prototype chip. Finally, we demonstrate the use of the neuromorphic processor with a convolutional neural network for the real-time classification of visual symbols being flashed to a dynamic vision sensor (DVS) at high speed.
Tasks
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04198v2
PDF	http://arxiv.org/pdf/1708.04198v2.pdf
PWC	https://paperswithcode.com/paper/a-scalable-multi-core-architecture-with
Repo
Framework

GOOWE: Geometrically Optimum and Online-Weighted Ensemble Classifier for Evolving Data Streams


Title	GOOWE: Geometrically Optimum and Online-Weighted Ensemble Classifier for Evolving Data Streams
Authors	Hamed R. Bonab, Fazli Can
Abstract	Designing adaptive classifiers for an evolving data stream is a challenging task due to the data size and its dynamically changing nature. Combining individual classifiers in an online setting, the ensemble approach, is a well-known solution. It is possible that a subset of classifiers in the ensemble outperforms others in a time-varying fashion. However, optimum weight assignment for component classifiers is a problem which is not yet fully addressed in online evolving environments. We propose a novel data stream ensemble classifier, called Geometrically Optimum and Online-Weighted Ensemble (GOOWE), which assigns optimum weights to the component classifiers using a sliding window containing the most recent data instances. We map vote scores of individual classifiers and true class labels into a spatial environment. Based on the Euclidean distance between vote scores and ideal-points, and using the linear least squares (LSQ) solution, we present a novel, dynamic, and online weighting approach. While LSQ is used for batch mode ensemble classifiers, it is the first time that we adapt and use it for online environments by providing a spatial modeling of online ensembles. In order to show the robustness of the proposed algorithm, we use real-world datasets and synthetic data generators using the MOA libraries. First, we analyze the impact of our weighting system on prediction accuracy through two scenarios. Second, we compare GOOWE with 8 state-of-the-art ensemble classifiers in a comprehensive experimental environment. Our experiments show that GOOWE provides improved reactions to different types of concept drift compared to our baselines. The statistical tests indicate a significant improvement in accuracy, with conservative time and memory requirements.
Tasks
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02800v1
PDF	http://arxiv.org/pdf/1709.02800v1.pdf
PWC	https://paperswithcode.com/paper/goowe-geometrically-optimum-and-online
Repo
Framework

Guidelines for Artificial Intelligence Containment


Title	Guidelines for Artificial Intelligence Containment
Authors	James Babcock, Janos Kramar, Roman V. Yampolskiy
Abstract	With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community. Building on our previous work on AI Containment Problem we propose a number of guidelines which should help AI safety researchers to develop reliable sandboxing software for intelligent programs of all levels. Such safety container software will make it possible to study and analyze intelligent artificial agent while maintaining certain level of safety against information leakage, social engineering attacks and cyberattacks from within the container.
Tasks
Published	2017-07-24
URL	http://arxiv.org/abs/1707.08476v1
PDF	http://arxiv.org/pdf/1707.08476v1.pdf
PWC	https://paperswithcode.com/paper/guidelines-for-artificial-intelligence
Repo
Framework

Entropy-difference based stereo error detection


Title	Entropy-difference based stereo error detection
Authors	Subhayan Mukherjee, Irene Cheng, Ram Mohana Reddy Guddeti, Anup Basu
Abstract	Stereo depth estimation is error-prone; hence, effective error detection methods are desirable. Most such existing methods depend on characteristics of the stereo matching cost curve, making them unduly dependent on functional details of the matching algorithm. As a remedy, we propose a novel error detection approach based solely on the input image and its depth map. Our assumption is that, entropy of any point on an image will be significantly higher than the entropy of its corresponding point on the image’s depth map. In this paper, we propose a confidence measure, Entropy-Difference (ED) for stereo depth estimates and a binary classification method to identify incorrect depths. Experiments on the Middlebury dataset show the effectiveness of our method. Our proposed stereo confidence measure outperforms 17 existing measures in all aspects except occlusion detection. Established metrics such as precision, accuracy, recall, and area-under-curve are used to demonstrate the effectiveness of our method.
Tasks	Depth Estimation, Stereo Depth Estimation, Stereo Matching, Stereo Matching Hand
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10412v1
PDF	http://arxiv.org/pdf/1711.10412v1.pdf
PWC	https://paperswithcode.com/paper/entropy-difference-based-stereo-error
Repo
Framework

Approximation of Functions over Manifolds: A Moving Least-Squares Approach


Title	Approximation of Functions over Manifolds: A Moving Least-Squares Approach
Authors	Barak Sober, Yariv Aizenbud, David Levin
Abstract	We present an algorithm for approximating a function defined over a $d$-dimensional manifold utilizing only noisy function values at locations sampled from the manifold with noise. To produce the approximation we do not require any knowledge regarding the manifold other than its dimension $d$. We use the Manifold Moving Least-Squares approach of (Sober and Levin 2016) to reconstruct the atlas of charts and the approximation is built on-top of those charts. The resulting approximant is shown to be a function defined over a neighborhood of a manifold, approximating the originally sampled manifold. In other words, given a new point, located near the manifold, the approximation can be evaluated directly on that point. We prove that our construction yields a smooth function, and in case of noiseless samples the approximation order is $\mathcal{O}(h^{m+1})$, where $h$ is a local density of sample parameter (i.e., the fill distance) and $m$ is the degree of a local polynomial approximation, used in our algorithm. In addition, the proposed algorithm has linear time complexity with respect to the ambient-space’s dimension. Thus, we are able to avoid the computational complexity, commonly encountered in high dimensional approximations, without having to perform non-linear dimension reduction, which inevitably introduces distortions to the geometry of the data. Additionaly, we show numerical experiments that the proposed approach compares favorably to statistical approaches for regression over manifolds and show its potential.
Tasks	Dimensionality Reduction
Published	2017-11-02
URL	https://arxiv.org/abs/1711.00765v4
PDF	https://arxiv.org/pdf/1711.00765v4.pdf
PWC	https://paperswithcode.com/paper/approximation-of-functions-over-manifolds-a
Repo
Framework

Do Convolutional Neural Networks Learn Class Hierarchy?


Title	Do Convolutional Neural Networks Learn Class Hierarchy?
Authors	Bilal Alsallakh, Amin Jourabloo, Mao Ye, Xiaoming Liu, Liu Ren
Abstract	Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class confusion patterns follow a hierarchical structure over the classes. We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data. We found that this hierarchy not only dictates the confusion patterns between the classes, it furthermore dictates the learning behavior of CNNs. In particular, the early layers in these networks develop feature detectors that can separate high-level groups of classes quite well, even after a few training epochs. In contrast, the latter layers require substantially more epochs to develop specialized feature detectors that can separate individual classes. We demonstrate how these insights are key to significant improvement in accuracy by designing hierarchy-aware CNNs that accelerate model convergence and alleviate overfitting. We further demonstrate how our methods help in identifying various quality issues in the training data.
Tasks	Image Classification
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06501v1
PDF	http://arxiv.org/pdf/1710.06501v1.pdf
PWC	https://paperswithcode.com/paper/do-convolutional-neural-networks-learn-class
Repo
Framework

Quantized Memory-Augmented Neural Networks


Title	Quantized Memory-Augmented Neural Networks
Authors	Seongsik Park, Seijoon Kim, Seil Lee, Ho Bae, Sungroh Yoon
Abstract	Memory-augmented neural networks (MANNs) refer to a class of neural network models equipped with external memory (such as neural Turing machines and memory networks). These neural networks outperform conventional recurrent neural networks (RNNs) in terms of learning long-term dependency, allowing them to solve intriguing AI tasks that would otherwise be hard to address. This paper concerns the problem of quantizing MANNs. Quantization is known to be effective when we deploy deep models on embedded systems with limited resources. Furthermore, quantization can substantially reduce the energy consumption of the inference procedure. These benefits justify recent developments of quantized multi layer perceptrons, convolutional networks, and RNNs. However, no prior work has reported the successful quantization of MANNs. The in-depth analysis presented here reveals various challenges that do not appear in the quantization of the other networks. Without addressing them properly, quantized MANNs would normally suffer from excessive quantization error which leads to degraded performance. In this paper, we identify memory addressing (specifically, content-based addressing) as the main reason for the performance degradation and propose a robust quantization method for MANNs to address the challenge. In our experiments, we achieved a computation-energy gain of 22x with 8-bit fixed-point and binary quantization compared to the floating-point implementation. Measured on the bAbI dataset, the resulting model, named the quantized MANN (Q-MANN), improved the error rate by 46% and 30% with 8-bit fixed-point and binary quantization, respectively, compared to the MANN quantized using conventional techniques.
Tasks	Quantization
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03712v1
PDF	http://arxiv.org/pdf/1711.03712v1.pdf
PWC	https://paperswithcode.com/paper/quantized-memory-augmented-neural-networks
Repo
Framework

Person Recognition using Smartphones’ Accelerometer Data


Title	Person Recognition using Smartphones’ Accelerometer Data
Authors	Thingom Bishal Singha, Rajsekhar Kumar Nath, A. V. Narsimhadhan
Abstract	Smartphones have become quite pervasive in various aspects of our daily lives. They have become important links to a host of important data and applications, which if compromised, can lead to disastrous results. Due to this, today’s smartphones are equipped with multiple layers of authentication modules. However, there still lies the need for a viable and unobtrusive layer of security which can perform the task of user authentication using resources which are cost-efficient and widely available on smartphones. In this work, we propose a method to recognize users using data from a phone’s embedded accelerometer sensors. Features encapsulating information from both time and frequency domains are extracted from walking data samples, and are used to build a Random Forest ensemble classification model. Based on the experimental results, the resultant model delivers an accuracy of 0.9679 and Area under Curve (AUC) of 0.9822.
Tasks	Person Recognition
Published	2017-11-13
URL	http://arxiv.org/abs/1711.04689v1
PDF	http://arxiv.org/pdf/1711.04689v1.pdf
PWC	https://paperswithcode.com/paper/person-recognition-using-smartphones
Repo
Framework

A Realistic Dataset for the Smart Home Device Scheduling Problem for DCOPs


Title	A Realistic Dataset for the Smart Home Device Scheduling Problem for DCOPs
Authors	William Kluegel, Muhammad Aamir Iqbal, Ferdinando Fioretto, William Yeoh, Enrico Pontelli
Abstract	The field of Distributed Constraint Optimization has gained momentum in recent years thanks to its ability to address various applications related to multi-agent cooperation. While techniques to solve Distributed Constraint Optimization Problems (DCOPs) are abundant and have matured substantially since the field inception, the number of DCOP realistic applications and benchmark used to asses the performance of DCOP algorithms is lagging behind. To contrast this background we (i) introduce the Smart Home Device Scheduling (SHDS) problem, which describe the problem of coordinating smart devices schedules across multiple homes as a multi-agent system, (ii) detail the physical models adopted to simulate smart sensors, smart actuators, and homes environments, and (iii) introduce a DCOP realistic benchmark for SHDS problems.
Tasks
Published	2017-02-22
URL	http://arxiv.org/abs/1702.06970v1
PDF	http://arxiv.org/pdf/1702.06970v1.pdf
PWC	https://paperswithcode.com/paper/a-realistic-dataset-for-the-smart-home-device
Repo
Framework

Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks


Title	Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks
Authors	Yi Han, Benjamin I. P. Rubinstein
Abstract	Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks—carefully crafted adversarial samples that closely resemble legitimate instances, but cause misclassification. In this paper, we examine the adequacy of the leading approach to generating adversarial samples—the gradient descent approach. In particular (1) we perform extensive experiments on three datasets, MNIST, USPS and Spambase, in order to analyse the effectiveness of the gradient-descent method against non-linear support vector machines, and conclude that carefully reduced kernel smoothness can significantly increase robustness to the attack; (2) we demonstrate that separated inter-class support vectors lead to more secure models, and propose a quantity similar to margin that can efficiently predict potential susceptibility to gradient-descent attacks, before the attack is launched; and (3) we design a new adversarial sample construction algorithm based on optimising the multiplicative ratio of class decision functions.
Tasks
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01704v2
PDF	http://arxiv.org/pdf/1704.01704v2.pdf
PWC	https://paperswithcode.com/paper/adequacy-of-the-gradient-descent-method-for
Repo
Framework