检索结果-内蒙古大学图书馆

International Conference on Knowledge-Based Intelligent Electronic systems (KES)

作者： T. Hossain T.S. Dillon Expert and Intelligent Systems Laboratory Applied Computing Research Institute and School of Computer Science & Computer Engineering La Trobe University Bundoora Australia

The paper examines several methods for improving the generalization capability of the BRAINNE technique. These methods deal with proper training of neural networks and improvements in defining bounds for continuous data.

关键词： Biological neural networks Multi-layer neural network Neural networks Intelligent networks Intelligent systems computer networks Noise measurement Particle measurements Laboratories computer science

来源：评论

学校读者我要写书评

暂无评论

An efficient local address generation for the block-cyclic distribution 3

An efficient local address generation for the block-cyclic d...

引用

3rd International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 1997

作者： Kwon, Oh-Young Kim, Tae-Geun Han, Tack-Don Yang, Sung-Bong Kim, Shin-Dug Distributed Computing Lab. Systems Engineering Research Institute 1 Ueun-dong Yusong-gu Taejon305-333 Korea Republic of Parallel Processing System Laboratory Dept. of Computer Science Yonsei University Seoul120-749 Korea Republic of

ISBN: (纸本)0780342291

In order to generate local addresses for an array section A(l:h:s) with block-cyclic distribution, an efficient compiling method is required. In this paper, two local address generation methods for the block-cyclic distribution are presented. One is a simple local address generation method that is modified from the virtual-block scheme. The other is a linear-time ΔM table construction method. The array elements of A(l:h:s) to be accessed at run-time build up a family of lines. By using the equation of the lines, a ΔM table can be generated in O(k) time. Experimental results show that a simple local address generation method has poor performance but a linear-time ΔM table generation method is faster than other algorithms in ΔM table generation time and access time for 10,000 array elements. © 1997 IEEE.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

Fusion of knowledge-based systems and neural networks and applications

Fusion of knowledge-based systems and neural networks and ap...

引用

International Conference on Knowledge-Based Intelligent Electronic systems (KES)

作者： R. Khosla T. Dillon Expert and Intelligent Systems Laboratory Applied Computing Research Institute and Department of Computer Science and Computer Engineering La Trobe University Melbourne VIC Australia

Neural Networks and Symbolic Knowledge-Based systems each have their strengths and weaknesses. Intelligent systems that fuse these two paradigms overcome a significant number of the weaknesses of each individual paradigm. There are many different approaches in the literature (including research from the author's own group) to fusing these paradigms. A critical evaluation of these approaches is given within the paper.

关键词： Knowledge based systems Neural networks Intelligent networks Humans Artificial neural networks Artificial intelligence Problem-solving Application software Intelligent systems computer networks

来源：评论

学校读者我要写书评

暂无评论

An efficient local address generation for the block-cyclic distribution

An efficient local address generation for the block-cyclic d...

引用

IEEE International Conference on Algorithms and Architectures for Parallel Processing (ICAP)

作者： Oh-Young Kwon Tae-Geun Kim Tack-Don Han Sung-Bong Yang Shin-Dug Kim Distributed Computing Laboratory Systems Engineering Research Institute Taejon South Korea Parallel Processing System Laboratory Department of Computer Science Yonsei University Seoul South Korea

ISBN: (纸本)0780342291

In order to generate local addresses for an array section A(l:h:s) with block-cyclic distribution, an efficient compiling method is required. In this paper, two local address generation methods for the block-cyclic distribution are presented. One is a simple local address generation method that is modified from the virtual-block scheme. The other is a linear-time /spl Delta/M table construction method. The array elements of A(l:h:s) to be accessed at run-time build up a family of lines. By using the equation of the lines, a /spl Delta/M table can be generated in O(k) time. Experimental results show that a simple local address generation method has poor performance but a linear-time /spl Delta/M table generation method is faster than other algorithms in /spl Delta/M table generation time and access time for 10,000 array elements.

关键词： Runtime Equations Distributed computing systems engineering and theory Parallel processing Laboratories computer science Parallel languages Upper bound Automata

来源：评论

学校读者我要写书评

暂无评论

MTIO. A multi-threaded parallel I/O system

MTIO. A multi-threaded parallel I/O system

引用

International Symposium on Parallel Processing

作者： S. More A. Choudhary I. Foster M.Q. Xu Departmentof Electrical and Computer Engineering Northwestern University Evanston IL USA Mathematics and Computer Science Division Argonne National Laboratory Argonne IL USA Platform Computing Inc. North York ONT Canada

Presents the design and evaluation of MTIO (Multi-Threaded Input/Output), a multi-threaded runtime library for parallel I/O. We extend the multi-threading concept to separate the computation and I/O tasks into two separate threads of control. Multi-threading in our design permits (a) asynchronous I/O even if the underlying file system does not support asynchronous I/O; (b) copy avoidance from the I/O thread to the compute thread by sharing address space; and (c) a capability to perform collective I/O asynchronously without blocking the compute threads. Further, this paper presents techniques for collective I/O which maximize load balance and concurrency while reducing communication overhead in an integrated fashion. Performance results on an IBM SP2 for various data distributions and access patterns are presented. The results show that there is a tradeoff between the amount of concurrency in I/O and the buffer size designated for I/O, and that there is an optimal buffer size beyond which the benefits of larger requests diminish due to large communication overheads.

关键词： Yarn Concurrent computing File systems Runtime library Control systems Physics computing Design optimization Design engineering Mathematics computer science

来源：评论

学校读者我要写书评

暂无评论

Parallel execution of radix sort program using fine-grain communication

Parallel execution of radix sort program using fine-grain co...

引用

International Conference on Parallel Architecture and Compilation Techniques (PACT)

作者： Y. Kodama M. Sato H. Sakane S. Sakai K. Hanpei Y. Yamaguchi Computer Science Division Electro Technical Laboratory Tsukuba Japan Real World Computing Tsukuba Research Center Tsukuba Japan Institute of Info. Science and Elec. University of Tsukuba Tsukuba Japan

The report presents empirical results of fine-grain communication on the 80-processor EM-X distributed-memory multiprocessor. EM-X has hardware support for low latency, high throughput fine-grain communication-this hardware support includes packet generation integrated into the instruction execution pipeline for single-cycle communication overhead, direct memory access for remote references, and rapid context switching for latency tolerance. The authors study the fine-grain communication performance of integer radix sort, a code with irregular communication, on EM-X, and compare it to the Fujitsu AP1000+ and the Cray Server CS6400. The experimental results indicate that EM-X achieves high throughput and low overhead for fine-grain communication. Whereas EM-X's communication performance scales perfectly as one increases the number of processors, other coarse-grain message-passing machines exhibit fluctuation and performance degradation for larger configurations due to network contention.

关键词： Hardware Delay Throughput Pipelines Context Packet switching Communication switching Network servers Fluctuations Degradation

来源：评论

学校读者我要写书评

暂无评论

Modeling of a highly reliable real-time distributed system using the RTO.k model and the monitor object

Modeling of a highly reliable real-time distributed system u...

引用

Workshop on Object-Oriented Real-Time Dependable systems (WORDS)

作者： Moon Hae Kim Yong-Min Park Seung-Min Yang Jong-Kook Park Department of Computer Science & Engineering Konkuk University Seoul South Korea Konkuk University Gwangjin-gu Seoul KR Computer Science Division Soongsil University Seoul South Korea Power Systems Laboratory LG Industrial Systems Company Limited Kyunggi South Korea

ISBN: (纸本)0818680466

The main focus of this paper is the modeling of a highly reliable real-time distributed system using the RTO.k (Real-Time Object) model incorporating the monitor approach. The RTO.k model is used to specify the real-time distributed nature of the system, while the monitor is used to support reliable operations of the system. A monitor is an abstract software component to handle faults occurring during the system's operation. It can be modeled as an RTO.k object called a real-time monitor object (RTMO). In this paper, we present three basic structuring schemes with an RTO.k object and an RTMO. Our modeling approach utilizes these structuring schemes. To illustrate our approach, KODAS (KOrea Distribution Automation System), being developed at LG Industrial systems Co. Ltd., is used. In order to examine the effectiveness of our approach, we have designed a simulation model for KODAS and implemented it on the DREAM kernel. The RTO.k model and the monitor approach can be easily incorporated, and can be integrated as a set of RTO.k objects so as to facilitate the modeling of a highly reliable real-time distributed system.

关键词： Real time systems Power system modeling Power system reliability Kernel Fault detection computerized monitoring computer science Event detection Moon Industrial power systems

来源：评论

学校读者我要写书评

暂无评论

Application of a Load Distribution Technique for Contact Force Magnitude Limit Avoidance when Two Manipulators Mutually Lift a Rigid Object

引用

Intelligent Automation and Soft computing 1997年第4期3卷 363-378页

作者： Unseren, Michael A. Computational Intelligence Group Intelligent Systems Section Computer Science and Mathematics Division Oak Ridge National Laboratory Oak Ridge TN United States

In our previous work, a new technique for dynamically distributing the load imposed by a rigid object between two manipulators which mutually hold the object was proposed. The technique was applied given two different choices of a designer specified matrix, and in each case it resulted in an optimal solution for the contact forces and torque imparted to the object by the manipulators. Each contact force solution contains an object motion inducing component and an internal stress and torsion inducing component. The internal component is a linear function of a vector of “corrective” contact forces. This article addresses the problem of determining the corrective contact forces such that the internal component of the contact force solution contributes to contact force magnitude limit avoidance. The basic premise to our approach is that there is a maximum magnitude limit associated with each of the contact forces, and that a magnitude limit avoidance algorithm should be activated only when it is detected, by sensing, that one or more of the contact forces are in close proximity to their respective magnitude limits. Two algorithms for calculating the corrective contact forces are proposed and compared to determine their relative advantages. The article also presents several new insights into the modeling and optimization technique presented in our earlier work. © 1997 Taylor & Francis Group, LLC.

关键词： Corrective contact forces Cycloidal function Load distribution Magnitude limit avoidance Motion inducing and internal contact forces Two manipulators

来源：评论

学校读者我要写书评

暂无评论

Scalable hardware priority queue architectures for high-speed packet switches

Scalable hardware priority queue architectures for high-spee...

引用

Real-Time Technology and Applications Symposium

作者： S.-W. Moon K.G. Shin J. Rexford Real-Time Computing Laboratory Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA Network Mathematics Research Networking and Distributed Systems AT and T Research Laboratories Murray Hill NJ USA

In packet-switched networks, queueing of packets at the switches can result when multiple connections share the same physical link. To accommodate a large number of connections, a switch can employ link-scheduling algorithms to prioritize the transmission of the queued packets. Due to the high-speed links and small packet sizes, a hardware solution is needed for the priority queue in order to make the link schedulers effective. But for good performance, the switch should also support a large number of priority levels (P) and be able to buffer a large number of packets (N). So a hardware priority queue design must be both fast and scalable (with respect to N and P) in order to be implemented effectively. In this paper we first compare four existing hardware priority queue architectures, and identify scalability limitations on implementing these existing architectures for large N and P. Based on our findings, we propose two new priority queue architectures, and evaluate them using simulation results from Verilog HDL and Epoch implementations.

关键词： Packet switching Switches Traffic control Scheduling algorithm Asynchronous transfer mode Hardware design languages Communication system traffic control computer architecture Moon Real time systems

来源：评论

学校读者我要写书评

暂无评论

Emergence and Effectiveness of Communication Interface in a System of Distributed Intelligent Agents

引用

Journal of Robotics and Mechatronics 1997年第2期9卷 146-151页

作者： Agah, Arvin Bekey, George A. Bio-Robotics Division Mechanical Engineering Laboratory AIST- Ministry of International Trade and Industry 1-2 Namiki Tsukuba305 Japan Institute for Robotics and Intelligent Systems Computer Science Department University of Southern California Los AngelesCA90089 United States

The emergence and effectiveness of communication interface in a colony of autonomous agents is discussed in this paper. The robotic agents sense the world within which they are embedded, while performing specific tasks in the world. Some of the tasks require the simultaneous cooperation of two robotic agents. These agents are able to sense other agents and communicate via simple, task-related messages. Using genetic algorithms, a colony of agents is evolved, producing agents with improved performance. It is shown that the tendency of the robotics agents to communicate increases through evolution, as the colony cooperates more, in order to perform more tasks. The concepts developed through computer simulation are tested for feasibility in a team of four small mobile-manipulator robots, each controlled autonomously via an on-board micro-processor. © Fuji Technology Press Ltd.

关键词： Multi agent systems

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：