检索结果-内蒙古大学图书馆

An implementation, empirical evaluation and proposed improvement for bidirectional splitting method for argumentation frameworks under stable semantics

arXiv

引用

arXiv 2018年

作者： Wong, Renata Department of Computer Science and Technology Nanjing University Nanjing China State Key Laboratory for Novel Software Technology at Nanjing University Nanjing China

Abstract argumentation frameworks are formal systems that facilitate obtaining conclusions from non-monotonic knowledge systems. Within such a system, an argumentation semantics is defined as a set of arguments with some desired qualities, for example, that the elements are not in conflict with each other. Splitting an argumentation framework can efficiently speed up the computation of argumentation semantics. With respect to stable semantics, two methods have been proposed to split an argumentation framework either in a unidirectional or bidirectional fashion. The advantage of bidirectional splitting is that it is not structure-dependent and, unlike unidirectional splitting, it can be used for frameworks consisting of a single strongly connected component. Bidirectional splitting makes use of a minimum cut. In this paper, we implement and test the performance of the bidirectional splitting method, along with two types of graph cut algorithms. Experimental data suggest that using a minimum cut will not improve the performance of computing stable semantics in most cases. Hence, instead of a minimum cut, we propose to use a balanced cut, where the framework is split into two sub-frameworks of equal size. Experimental results conducted on bidirectional splitting using the balanced cut show a significant improvement in the performance of computing *** Codes 68T30 Copyright © 2018, The Authors. All rights reserved.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Improved Upper Bound on the Network Function Computing Capacity

Improved Upper Bound on the Network Function Computing Capac...

引用

作者： Guang, Xuan Yeung, Raymond W. Yang, Shenghao Li, Congduan School of Mathematical Sciences and LPMC Nankai University Tianjin300071 China Institute of Network Coding Chinese University of Hong Kong Hong Kong Hong Kong Department of Information Engineering Chinese University of Hong Kong Hong Kong Hong Kong School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China School of Electronics and Communication Engineering Sun Yat-sen University Guangzhou510006 China

The problem of network function computation over a directed acyclic network is investigated in this paper. In such a network, a sink node desires to compute with zero error a target function, of which the inputs are generated at multiple source nodes. The edges in the network are assumed to be error-free and have limited capacity. The nodes in the network are assumed to have unbounded computing capability and be able to perform network coding. The computing rate of a network code that can compute the target function over the network is the average number of times that the target function is computed with zero error for one use of the network. In this paper, we obtain an improved upper bound on the computing capacity, which is applicable to arbitrary target functions and arbitrary network topologies. This improved upper bound not only is an enhancement of the previous upper bounds but also is the first tight upper bound on the computing capacity for computing an arithmetic sum over a certain non-tree network, which has been widely studied in the literature. We also introduce a multi-dimensional array approach that facilitates evaluation of the improved upper bound. Furthermore, we apply this bound to the problem of computing a vector-linear function over a network. With this bound, we are not only able to enhance a previous result on computing a vector-linear function over a network but also simplify the proof significantly. Finally, we prove that for computing the binary maximum function over the reverse butterfly network, our improved upper bound is not achievable. This result establishes that in general our improved upper bound is non-achievable, but whether it is asymptotically achievable or not remains open. © 1963-2012 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Opinion target extraction for the Chinese formal text based on dependency relations 1st

Opinion target extraction for the Chinese formal text based ...

引用

1st International Conference on Smart Vehicular technology, Transportation, Communication and Applications, VTCA 2017

作者： Yang, Xiao-Yan Xu, Ge Zhang, Fu-Quan Liao, Xiang-Wen Xu, Lin Department of Computer Science Minjiang University FuzhouFujian350121 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control FuzhouFujian350121 China School of Software Beijing Institute of Technology Beijing10081 China College of Mathematics and Computer Science Fuzhou University FuzhouFujian350108 China Innovative Information Industry Research Institute Fujian Normal University FuzhouFujian350300 China

ISBN: (纸本)9783319707297

Due to the increasing amount of opinion data on the internet, opinion mining has become a hot topic, in which extracting opinion targets is a key step. The state-of-the-art approaches only use direct dependency relation patterns to extract opinion targets and the indirect dependency relation patterns have not been used. In this paper, the dependency relations between opinion target and opinion word are defined, and direct and indirect dependency relation patterns are designed. Then, a bootstrapping approach is used to extract and evaluate both candidate patterns and opinion targets. The experimental results show that in formal text, the approach improves the performance compared with the state-of-the-art approaches for opinion target extraction. © Springer International Publishing AG 2018.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Voltage-Controlled Spintronic Stochastic Neuron Based on a Magnetic Tunnel Junction

引用

Physical Review Applied 2019年第3期11卷 034015-034015页

作者： Jialin Cai Bin Fang Like Zhang Wenxing Lv Baoshun Zhang Tiejun Zhou Giovanni Finocchio Zhongming Zeng Key Laboratory of Multifunctional Nanomaterials and Smart Systems Suzhou Institute of Nano-Tech and Nano-Bionics CAS Suzhou Jiangsu 215123 People’s Republic of China School of Nano Technology and Nano Bionics University of Science and Technology of China Hefei Anhui 230026 People’s Republic of China College of Electronics and Information Hangzhou Dianzi University Hangzhou 310018 People’s Republic of China Department of Mathematical and Computer Sciences Physical Sciences and Earth Sciences University of Messina Messina 98166 Italy

Stochastic units based on magnetic tunnel junctions have shown a high energy-efficient pathway to perform neuromorphic computing. We propose a voltage-controlled spintronic stochastic device based on a magnetic tunnel junction by introducing perpendicular anisotropy into the free layer. We observe a stochastic behavior at low bias and demonstrate that this behavior can be used to mimic the artificial neurons of an artificial neural network to recognize the handwritten digits in the Mixed National Institute of Standards and technology (MNIST) database. Furthermore, the stochastic behavior can be modulated by a bias voltage owing to the voltage-controlled magnetic anisotropy effect. The voltage-controlled stochastic behavior is theoretically and experimentally studied, which indicates that it can be used to perform as an adaptive neuron. These results provide a way for building energy-efficient spintronic neuromorphic computing systems.

关键词： Magnetization switching Spintronics Artificial neural networks Magnetic tunnel junctions Ferromagnetic resonance Magnetization measurements Spiking neuron models

来源：评论

学校读者我要写书评

暂无评论

Understanding co-run performance on CPU-GPU integrated processors： observations, insights, directions

引用

Frontiers of computer science 2017年第1期11卷 130-146页

作者： Qi ZHU Bo WU Xipeng SHEN Kai SHEN Li SHEN Zhiying WANG National Key Laboratory of High Performance Computing National University of Defense Technology Changsha 410073 China Department of Computer Science North Carolina State University Raleigh NC 27695 USA Department of Electrical Engineering & Computer Science Colorado School of Mines Golden CO 80401 USA Department of Computer Science University of Rochester Rochester NY 14627 USA

Recent years have witnessed a processor develop- ment trend that integrates central processing unit （CPU） and graphic processing unit （GPU） into a single chip. The inte- gration helps to save some host-device data copying that a discrete GPU usually requires, but also introduces deep re- source sharing and possible interference between CPU and GPU. This work investigates the performance implications of independently co-running CPU and GPU programs on these platforms. First, we perform a comprehensive measurement that covers a wide variety of factors, including processor ar- chitectures, operating systems, benchmarks, timing mecha- nisms, inputs, and power management schemes. These mea- surements reveal a number of surprising observations. We an- alyze these observations and produce a list of novel insights, including the important roles of operating system （OS） con- text switching and power management in determining the program performance, and the subtle effect of CPU-GPU data copying. Finally, we confirm those insights through case studies, and point out some promising directions to mitigate anomalous performance degradation on integrated heteroge- neous processors.

关键词： performance analysis GPGPU co-run degrada-tion fused processor program transformation

来源：评论

学校读者我要写书评

暂无评论

Person search via a mask-guided two-stream CNN model

arXiv

引用

arXiv 2018年

作者： Chen, Di Zhang, Shanshan Ouyang, Wanli Yang, Jian Tai, Ying PCA Lab Key Lab of Intelligent Perception Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image School of Computer Science and Engineering Nanjing University of Science and Technology University of Sydney Sensetime Intelligent Multimedia Laboratory Group Youtu Lab Tencent

In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification (re-ID). Instead of sharing representations in a single joint model, we find that separating detector and re-ID feature extraction yields better performance. In order to extract more representative features for each identity, we propose a simple yet effective re-ID method, which models foreground person and original image patches individually, and obtains enriched representations from two separate CNN streams. On the standard person search benchmark datasets, we achieve mAP of 83:0% and 32:6% respectively for CUHK-SYSU and PRW, surpassing the state of the art by a large margin (more than 5pp). Copyright © 2018, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Object Proposal Generation for Unsupervised Object Localization

Object Proposal Generation for Unsupervised Object Localizat...

引用

International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)

作者： Wenzhong Guo Renjie Lin Shiping Wang Neal Xiong Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Department of Mathematics and Computer Science Northeastern State University Tahlequah USA

ISBN: (纸本)9781538694046;9781538694039

Object proposals has become the preprocessing in many vision pipelines especially in object localization systems. While with the development and widespread of proposal localization, it is hard to decide which method is more suitable for object detection. In this paper we provide detailed understanding about differences of five object proposal methods. And we provide a set of evaluation metrics and use these metrics to compare and evaluate the recall situation of these object proposal methods. Using the ground-truth instance for exploring unsupervised object localization on PASCAL VOC 2007, MSRA10K and Object Discovery datasets. Our experimental analysis demonstrates that the performance of these methods depends on the number of candidates and the threshold of recall, meanwhile the methods that generate the candidates with scores perform better than those methods that do not with scores. Our findings show the advantages and disadvantages of these methods, and provide insights and metrics to motivate the evaluation of object proposal methods.

关键词： Proposals Image edge detection Microsoft Windows Image color analysis Measurement Histograms Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Attentive relational networks for mapping images to scene graphs

arXiv

引用

arXiv 2018年

作者： Qi, Mengshi Li, Weijian Yang, Zhengyuan Wang, Yunhong Luo, Jiebo State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Department of Computer Science University of Rochester United States

Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships. Despite the recent success in object detection using deep learning techniques, inferring complex contextual relationships and structured graph representations from visual data remains a challenging topic. In this study, we propose a novel Attentive Relational Network that consists of two key modules with an object detection backbone to approach this problem. The first module is a semantic transformation module utilized to capture semantic embedded relation features, by translating visual features and linguistic features into a common semantic space. The other module is a graph self-attention module introduced to embed a joint graph representation through assigning various importance weights to neighboring nodes. Finally, accurate scene graphs are produced by the relation inference module to recognize all entities and the corresponding relations. We evaluate our proposed method on the widely-adopted Visual Genome Dataset, and the results demonstrate the effectiveness and superiority of our model. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Evaluating accuracy of Hessian-based predictor-corrector integrators

引用

Journal of Central South University 2017年第7期24卷 1696-1702页

作者： LU Shao-fei WU Heng LIU Xu-chong College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China Department of Computer Science Texas Tech UniversityLubbock 79409USA Department of Computer Science Midwestern State UniversityWichita Falls 76308USA Hunan Provincial Key Laboratory of Network Investigational Technology Hunan Police AcademyChangsha 410138China

Direct dynamics simulations are a useful and general approach for studying the atomistic properties of complex chemical systems because they do not require fitting an analytic potential energy ***-based predictor-corrector integrators are a widely used approach for calculating the trajectories of moving atoms in direct dynamics *** employ a monodromy matrix to propose a tool for evaluating the accuracy of integrators in the trajectory *** choose a general velocity Verlet as a different *** also simulate molecular with hydrogen(CO_2) and molecular with hydrogen(H_2O) *** the eigenvalues of monodromy matrix,many simulations show that Hessian-based predictor-corrector integrators perform well for Hessian updates and non-Hessian ***-based predictor-corrector integrator with Hessian update has a strong performance in the H_2O ***-based predictor-corrector integrator with Hessian update has a strong performance when the integrating step of the velocity Verlet approach is tripled for the predicting *** the CO_2 simulations,a strong performance occurs when the integrating step is a multiple of five.

关键词： monodromy matrix eigenvalue Hessian-based predictor-corrector velocity Verlet

来源：评论

学校读者我要写书评

暂无评论

Varying control intensity of synchronized chaotic system with time delay

引用

Journal of Physics: Conference Series 2021年第1期1828卷

作者： Babatunde O. Onasanya Shiping Wen Yuming Feng Wei Zhang Ning Tang Adeleke T. Ademola Key Laboratory of Intelligent Information Processing and Control Chongqing Three Gorges University Wanzhou Chongqing 404100 China Department of Mathematics University of Ibadan Ibadan Nigeria Australian AI Institute University of Technology Sydney Ultimo NSW 2007 Australia School of Computer Science and Engineering Chongqing Three Gorges University Wanzhou Chongqing 404100 China Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Chongqing Three Gorges University Wanzhou Chongqing 404100 China School of Three Gorges Artificial Intelligence Chongqing Three Gorges University Wanzhou Chongqing 404100 China Department of Mathematics Obafemi Awolowo University Post Code 220005 Ile-Ife Nigeria

Hyperchaotic system is a very useful tool in secure and encrypted communications. But situations arise when engineers and scientists seek to synchronize two hyperchaotic systems. This gives another (error) system. The goal is to minimize the error as much as can be in order to make one system look like the other by synchronization. This is a particularly challenging situation. In this paper, two hyperchaotic systems are synchronized by impulsive control. Also, the condition for uniform asymptotic stability of the synchronized error system was given. Finally, the simulation results to justify the reliability of this method is also presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：