July 27, 2019

2703 words 13 mins read

Paper Group ANR 545

Neural Class-Specific Regression for face verification. Geo-referencing Place from Everyday Natural Language Descriptions. Detecting Intentional Lexical Ambiguity in English Puns. A Two-Phase Genetic Algorithm for Image Registration. Artificial Intelligence Based Malware Analysis. Dynamic Partition Models. Reinforcement Learning Based Argument Comp …

Neural Class-Specific Regression for face verification


Title	Neural Class-Specific Regression for face verification
Authors	Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj
Abstract	Face verification is a problem approached in the literature mainly using nonlinear class-specific subspace learning techniques. While it has been shown that kernel-based Class-Specific Discriminant Analysis is able to provide excellent performance in small- and medium-scale face verification problems, its application in today’s large-scale problems is difficult due to its training space and computational requirements. In this paper, generalizing our previous work on kernel-based class-specific discriminant analysis, we show that class-specific subspace learning can be cast as a regression problem. This allows us to derive linear, (reduced) kernel and neural network-based class-specific discriminant analysis methods using efficient batch and/or iterative training schemes, suited for large-scale learning problems. We test the performance of these methods in two datasets describing medium- and large-scale face verification problems.
Tasks	Face Verification
Published	2017-08-31
URL	http://arxiv.org/abs/1708.09642v1
PDF	http://arxiv.org/pdf/1708.09642v1.pdf
PWC	https://paperswithcode.com/paper/neural-class-specific-regression-for-face
Repo
Framework

Geo-referencing Place from Everyday Natural Language Descriptions


Title	Geo-referencing Place from Everyday Natural Language Descriptions
Authors	Hao Chen, Maria Vasardani, Stephan Winter
Abstract	Natural language place descriptions in everyday communication provide a rich source of spatial knowledge about places. An important step to utilize such knowledge in information systems is geo-referencing all the places referred to in these descriptions. Current techniques for geo-referencing places from text documents are using place name recognition and disambiguation; however, place descriptions often contain place references that are not known by gazetteers, or that are expressed in other, more flexible ways. Hence, the approach for geo-referencing presented in this paper starts from a place graph that contains the place references as well as spatial relationships extracted from place descriptions. Spatial relationships are used to constrain the locations of places and allow the later best-matching process for geo-referencing. The novel geo-referencing process results in higher precision and recall compared to state-of-art toponym resolution approaches on several tested place description datasets.
Tasks
Published	2017-10-09
URL	http://arxiv.org/abs/1710.03346v1
PDF	http://arxiv.org/pdf/1710.03346v1.pdf
PWC	https://paperswithcode.com/paper/geo-referencing-place-from-everyday-natural
Repo
Framework

Detecting Intentional Lexical Ambiguity in English Puns


Title	Detecting Intentional Lexical Ambiguity in English Puns
Authors	Elena Mikhalkova, Yuri Karyakin
Abstract	The article describes a model of automatic analysis of puns, where a word is intentionally used in two meanings at the same time (the target word). We employ Roget’s Thesaurus to discover two groups of words which, in a pun, form around two abstract bits of meaning (semes). They become a semantic vector, based on which an SVM classifier learns to recognize puns, reaching a score 0.73 for F-measure. We apply several rule-based methods to locate intentionally ambiguous (target) words, based on structural and semantic criteria. It appears that the structural criterion is more effective, although it possibly characterizes only the tested dataset. The results we get correlate with the results of other teams at SemEval-2017 competition (Task 7 Detection and Interpretation of English Puns) considering effects of using supervised learning models and word statistics.
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05468v1
PDF	http://arxiv.org/pdf/1707.05468v1.pdf
PWC	https://paperswithcode.com/paper/detecting-intentional-lexical-ambiguity-in
Repo
Framework

A Two-Phase Genetic Algorithm for Image Registration


Title	A Two-Phase Genetic Algorithm for Image Registration
Authors	Sarit Chicotay, Eli David, Nathan S. Netanyahu
Abstract	Image Registration (IR) is the process of aligning two (or more) images of the same scene taken at different times, different viewpoints and/or by different sensors. It is an important, crucial step in various image analysis tasks where multiple data sources are integrated/fused, in order to extract high-level information. Registration methods usually assume a relevant transformation model for a given problem domain. The goal is to search for the “optimal” instance of the transformation model assumed with respect to a similarity measure in question. In this paper we present a novel genetic algorithm (GA)-based approach for IR. Since GA performs effective search in various optimization problems, it could prove useful also for IR. Indeed, various GAs have been proposed for IR. However, most of them assume certain constraints, which simplify the transformation model, restrict the search space or make additional preprocessing requirements. In contrast, we present a generalized GA-based solution for an almost fully affine transformation model, which achieves competitive results without such limitations using a two-phase method and a multi-objective optimization (MOO) approach. We present good results for multiple dataset and demonstrate the robustness of our method in the presence of noisy data.
Tasks	Image Registration
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06765v1
PDF	http://arxiv.org/pdf/1711.06765v1.pdf
PWC	https://paperswithcode.com/paper/a-two-phase-genetic-algorithm-for-image
Repo
Framework

Artificial Intelligence Based Malware Analysis


Title	Artificial Intelligence Based Malware Analysis
Authors	Avi Pfeffer, Brian Ruttenberg, Lee Kellogg, Michael Howard, Catherine Call, Alison O’Connor, Glenn Takata, Scott Neal Reilly, Terry Patten, Jason Taylor, Robert Hall, Arun Lakhotia, Craig Miles, Dan Scofield, Jared Frank
Abstract	Artificial intelligence methods have often been applied to perform specific functions or tasks in the cyber-defense realm. However, as adversary methods become more complex and difficult to divine, piecemeal efforts to understand cyber-attacks, and malware-based attacks in particular, are not providing sufficient means for malware analysts to understand the past, present and future characteristics of malware. In this paper, we present the Malware Analysis and Attributed using Genetic Information (MAAGI) system. The underlying idea behind the MAAGI system is that there are strong similarities between malware behavior and biological organism behavior, and applying biologically inspired methods to corpora of malware can help analysts better understand the ecosystem of malware attacks. Due to the sophistication of the malware and the analysis, the MAAGI system relies heavily on artificial intelligence techniques to provide this capability. It has already yielded promising results over its development life, and will hopefully inspire more integration between the artificial intelligence and cyber–defense communities.
Tasks
Published	2017-04-27
URL	http://arxiv.org/abs/1704.08716v1
PDF	http://arxiv.org/pdf/1704.08716v1.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-based-malware
Repo
Framework

Dynamic Partition Models


Title	Dynamic Partition Models
Authors	Marc Goessling, Yali Amit
Abstract	We present a new approach for learning compact and intuitive distributed representations with binary encoding. Rather than summing up expert votes as in products of experts, we employ for each variable the opinion of the most reliable expert. Data points are hence explained through a partitioning of the variables into expert supports. The partitions are dynamically adapted based on which experts are active. During the learning phase we adopt a smoothed version of this model that uses separate mixtures for each data dimension. In our experiments we achieve accurate reconstructions of high-dimensional data points with at most a dozen experts.
Tasks
Published	2017-02-16
URL	http://arxiv.org/abs/1702.04832v1
PDF	http://arxiv.org/pdf/1702.04832v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-partition-models
Repo
Framework

Reinforcement Learning Based Argument Component Detection


Title	Reinforcement Learning Based Argument Component Detection
Authors	Yang Gao, Hao Wang, Chen Zhang, Wei Wang
Abstract	Argument component detection (ACD) is an important sub-task in argumentation mining. ACD aims at detecting and classifying different argument components in natural language texts. Historical annotations (HAs) are important features the human annotators consider when they manually perform the ACD task. However, HAs are largely ignored by existing automatic ACD techniques. Reinforcement learning (RL) has proven to be an effective method for using HAs in some natural language processing tasks. In this work, we propose a RL-based ACD technique, and evaluate its performance on two well-annotated corpora. Results suggest that, in terms of classification accuracy, HAs-augmented RL outperforms plain RL by at most 17.85%, and outperforms the state-of-the-art supervised learning algorithm by at most 11.94%.
Tasks
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06239v1
PDF	http://arxiv.org/pdf/1702.06239v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-based-argument
Repo
Framework

Satellite Image-based Localization via Learned Embeddings


Title	Satellite Image-based Localization via Learned Embeddings
Authors	Dong-Ki Kim, Matthew R. Walter
Abstract	We propose a vision-based method that localizes a ground vehicle using publicly available satellite imagery as the only prior knowledge of the environment. Our approach takes as input a sequence of ground-level images acquired by the vehicle as it navigates, and outputs an estimate of the vehicle’s pose relative to a georeferenced satellite image. We overcome the significant viewpoint and appearance variations between the images through a neural multi-view model that learns location-discriminative embeddings in which ground-level images are matched with their corresponding satellite view of the scene. We use this learned function as an observation model in a filtering framework to maintain a distribution over the vehicle’s pose. We evaluate our method on different benchmark datasets and demonstrate its ability localize ground-level images in environments novel relative to training, despite the challenges of significant viewpoint and appearance variations.
Tasks	Image-Based Localization
Published	2017-04-04
URL	http://arxiv.org/abs/1704.01133v1
PDF	http://arxiv.org/pdf/1704.01133v1.pdf
PWC	https://paperswithcode.com/paper/satellite-image-based-localization-via
Repo
Framework

Learning Unmanned Aerial Vehicle Control for Autonomous Target Following


Title	Learning Unmanned Aerial Vehicle Control for Autonomous Target Following
Authors	Siyi Li, Tianbo Liu, Chi Zhang, Dit-Yan Yeung, Shaojie Shen
Abstract	While deep reinforcement learning (RL) methods have achieved unprecedented successes in a range of challenging problems, their applicability has been mainly limited to simulation or game domains due to the high sample complexity of the trial-and-error learning process. However, real-world robotic applications often need a data-efficient learning process with safety-critical constraints. In this paper, we consider the challenging problem of learning unmanned aerial vehicle (UAV) control for tracking a moving target. To acquire a strategy that combines perception and control, we represent the policy by a convolutional neural network. We develop a hierarchical approach that combines a model-free policy gradient method with a conventional feedback proportional-integral-derivative (PID) controller to enable stable learning without catastrophic failure. The neural network is trained by a combination of supervised learning from raw images and reinforcement learning from games of self-play. We show that the proposed approach can learn a target following policy in a simulator efficiently and the learned behavior can be successfully transferred to the DJI quadrotor platform for real-world UAV control.
Tasks
Published	2017-09-24
URL	http://arxiv.org/abs/1709.08233v1
PDF	http://arxiv.org/pdf/1709.08233v1.pdf
PWC	https://paperswithcode.com/paper/learning-unmanned-aerial-vehicle-control-for
Repo
Framework

An Improved Algorithm for E-Generalization


Title	An Improved Algorithm for E-Generalization
Authors	Jochen Burghardt
Abstract	E-generalization computes common generalizations of given ground terms w.r.t. a given equational background theory E. In 2005 [arXiv:1403.8118], we had presented a computation approach based on standard regular tree grammar algorithms, and a Prolog prototype implementation. In this report, we present algorithmic improvements, prove them correct and complete, and give some details of an efficiency-oriented implementation in C that allows us to handle problems larger by several orders of magnitude.
Tasks
Published	2017-09-03
URL	http://arxiv.org/abs/1709.00744v1
PDF	http://arxiv.org/pdf/1709.00744v1.pdf
PWC	https://paperswithcode.com/paper/an-improved-algorithm-for-e-generalization
Repo
Framework

Neural-Symbolic Learning and Reasoning: A Survey and Interpretation


Title	Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
Authors	Tarek R. Besold, Artur d’Avila Garcez, Sebastian Bader, Howard Bowman, Pedro Domingos, Pascal Hitzler, Kai-Uwe Kuehnberger, Luis C. Lamb, Daniel Lowd, Priscila Machado Vieira Lima, Leo de Penning, Gadi Pinkas, Hoifung Poon, Gerson Zaverucha
Abstract	The study and understanding of human behaviour is relevant to computer science, artificial intelligence, neural computation, cognitive science, philosophy, psychology, and several other areas. Presupposing cognition as basis of behaviour, among the most prominent tools in the modelling of behaviour are computational-logic systems, connectionist models of cognition, and models of uncertainty. Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation. In addition, efforts in computer science research have led to the development of cognitive computational systems integrating machine learning and automated reasoning. Such systems have shown promise in a range of applications, including computational biology, fault diagnosis, training and assessment in simulators, and software verification. This joint survey reviews the personal ideas and views of several researchers on neural-symbolic learning and reasoning. The article is organised in three parts: Firstly, we frame the scope and goals of neural-symbolic computation and have a look at the theoretical foundations. We then proceed to describe the realisations of neural-symbolic computation, systems, and applications. Finally we present the challenges facing the area and avenues for further research.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03902v1
PDF	http://arxiv.org/pdf/1711.03902v1.pdf
PWC	https://paperswithcode.com/paper/neural-symbolic-learning-and-reasoning-a
Repo
Framework

PunFields at SemEval-2017 Task 7: Employing Roget’s Thesaurus in Automatic Pun Recognition and Interpretation


Title	PunFields at SemEval-2017 Task 7: Employing Roget’s Thesaurus in Automatic Pun Recognition and Interpretation
Authors	Elena Mikhalkova, Yuri Karyakin
Abstract	The article describes a model of automatic interpretation of English puns, based on Roget’s Thesaurus, and its implementation, PunFields. In a pun, the algorithm discovers two groups of words that belong to two main semantic fields. The fields become a semantic vector based on which an SVM classifier learns to recognize puns. A rule-based model is then applied for recognition of intentionally ambiguous (target) words and their definitions. In SemEval Task 7 PunFields shows a considerably good result in pun classification, but requires improvement in searching for the target word and its definition.
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05479v1
PDF	http://arxiv.org/pdf/1707.05479v1.pdf
PWC	https://paperswithcode.com/paper/punfields-at-semeval-2017-task-7-employing
Repo
Framework

DyVEDeep: Dynamic Variable Effort Deep Neural Networks


Title	DyVEDeep: Dynamic Variable Effort Deep Neural Networks
Authors	Sanjay Ganapathy, Swagath Venkataramani, Balaraman Ravindran, Anand Raghunathan
Abstract	Deep Neural Networks (DNNs) have advanced the state-of-the-art in a variety of machine learning tasks and are deployed in increasing numbers of products and services. However, the computational requirements of training and evaluating large-scale DNNs are growing at a much faster pace than the capabilities of the underlying hardware platforms that they are executed upon. In this work, we propose Dynamic Variable Effort Deep Neural Networks (DyVEDeep) to reduce the computational requirements of DNNs during inference. Previous efforts propose specialized hardware implementations for DNNs, statically prune the network, or compress the weights. Complementary to these approaches, DyVEDeep is a dynamic approach that exploits the heterogeneity in the inputs to DNNs to improve their compute efficiency with comparable classification accuracy. DyVEDeep equips DNNs with dynamic effort mechanisms that, in the course of processing an input, identify how critical a group of computations are to classify the input. DyVEDeep dynamically focuses its compute effort only on the critical computa- tions, while skipping or approximating the rest. We propose 3 effort knobs that operate at different levels of granularity viz. neuron, feature and layer levels. We build DyVEDeep versions for 5 popular image recognition benchmarks - one for CIFAR-10 and four for ImageNet (AlexNet, OverFeat and VGG-16, weight-compressed AlexNet). Across all benchmarks, DyVEDeep achieves 2.1x-2.6x reduction in the number of scalar operations, which translates to 1.8x-2.3x performance improvement over a Caffe-based implementation, with < 0.5% loss in accuracy.
Tasks
Published	2017-04-04
URL	http://arxiv.org/abs/1704.01137v1
PDF	http://arxiv.org/pdf/1704.01137v1.pdf
PWC	https://paperswithcode.com/paper/dyvedeep-dynamic-variable-effort-deep-neural
Repo
Framework

Multiresolution Kernel Approximation for Gaussian Process Regression


Title	Multiresolution Kernel Approximation for Gaussian Process Regression
Authors	Yi Ding, Risi Kondor, Jonathan Eskreis-Winkler
Abstract	Gaussian process regression generally does not scale to beyond a few thousands data points without applying some sort of kernel approximation method. Most approximations focus on the high eigenvalue part of the spectrum of the kernel matrix, $K$, which leads to bad performance when the length scale of the kernel is small. In this paper we introduce Multiresolution Kernel Approximation (MKA), the first true broad bandwidth kernel approximation algorithm. Important points about MKA are that it is memory efficient, and it is a direct method, which means that it also makes it easy to approximate $K^{-1}$ and $\mathop{\textrm{det}}(K)$.
Tasks
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02183v3
PDF	http://arxiv.org/pdf/1708.02183v3.pdf
PWC	https://paperswithcode.com/paper/multiresolution-kernel-approximation-for
Repo
Framework

Deep Neural Network Detects Quantum Phase Transition


Title	Deep Neural Network Detects Quantum Phase Transition
Authors	Shunta Arai, Masayuki Ohzeki, Kazuyuki Tanaka
Abstract	We detect the quantum phase transition of a quantum many-body system by mapping the observed results of the quantum state onto a neural network. In the present study, we utilized the simplest case of a quantum many-body system, namely a one-dimensional chain of Ising spins with the transverse Ising model. We prepared several spin configurations, which were obtained using repeated observations of the model for a particular strength of the transverse field, as input data for the neural network. Although the proposed method can be employed using experimental observations of quantum many-body systems, we tested our technique with spin configurations generated by a quantum Monte Carlo simulation without initial relaxation. The neural network successfully classified the strength of transverse field only from the spin configurations, leading to consistent estimations of the critical point of our model $\Gamma_c =J$.
Tasks
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00371v1
PDF	http://arxiv.org/pdf/1712.00371v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-network-detects-quantum-phase
Repo
Framework