检索结果-内蒙古大学图书馆

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

作者： Takahashi, E. Osuga, T. Taniguchi, K. Wakamiya, N. Service Platforms Research Laboratories NEC Corporation Japan Graduate School of Information Science and Technology Osaka University Japan

ISBN: (纸本)9781424411894

Point-to-multipoint bulk data transfer using application-layer multicast (ALM) is discussed. In ALM, each host participating in an application session makes copies of received data by application-layer manipulation and forwards the copies to other hosts via unicast connections. Therefore, the performance, especially for access link speed, of hosts strongly affects overall delivery performance. In heterogeneous access environments, there is a strong possibility that some hosts with low-speed links decrease overall delivery performance. However, many previous solutions constructed ALM trees by introducing arbitrary degree allocations and by not well considering a diversity of access link speeds of hosts. This paper proposes an algorithm to construct an efficient ALM tree from hosts with heterogeneous access lines. This algorithm minimizes delivery completion time and lets many hosts complete reception of all data as fast as possible. The effectiveness of the algorithm is verified using simulations.

关键词： hosts Access algorithms application layer constructive algorithm Heterogeneous reception

来源：评论

学校读者我要写书评

暂无评论

Ant colony optimisation for task matching and scheduling

引用

IEE PROCEEDINGS-COMPUTERS AND DIGITAL TECHNIQUES 2006年第6期153卷 373-380页

作者： Chiang, C-W. Lee, Y-C. Lee, C-N. Chou, T-Y. Natl Kaohsiung First Univ Sci & Technol Dept Comp & Commun Engn Kaohsiung 811 Taiwan Natl Sun Yat Sen Univ Dept Comp Sci & Engn Kaohsiung 804 Taiwan

PC clusters have recently received considerable interest as cost-effective parallel platforms for CPU-intensive applications. A cluster of PCs generally comprises of a collection of heterogeneous process elements (PEs). To make effective use of a PC cluster, a parallel program, which is characterised by a node- and edge-weighted directed acyclic graph (DAG), can usually be decomposed into a set of precedence-constrained atomic tasks such that PEs are able to accommodate these tasks and minimise the overall program-completion time. Consequently, techniques for task matching and scheduling become extremely important for effectively harnessing the computing power of the target cluster-based system. This work presents a constructive algorithm based on ant colony optimisation (ACO). The proposed algorithm, namely ACO-TMS, adopts a new state transition rule that reduces the time required when finding the satisfactory scheduling results. The proposed algorithm also integrates a local search procedure that proposed to help improve the scheduling results. The performance of this algorithm is demonstrated by comparing it against other existing algorithms, such as the genetic -algorithm-based scheduling method and the dynamic priority scheduling (DPS) heuristic, in terms of overall schedule length of randomly generated DAGs. Experimental results indicate that the proposed algorithm outperforms the genetic algorithm and the DPS heuristic algorithm for high communication to computation and heterogeneous computing environment.

关键词： constructive algorithm task scheduling optimisation PC clusters Combinatorial mathematics heterogeneous process element Optimisation techniques task matching processor scheduling ant colony optimisation search problems Distributed systems software parallel program state transition rule directed acyclic graph ACO-TMS CPU-intensive applications local search procedure directed graphs

来源：评论

学校读者我要写书评

暂无评论

Characterization of Cheeger sets for convex subsets of the plane

引用

PACIFIC JOURNAL OF MATHEMATICS 2006年第1期225卷 103-118页

作者： Kawohl, Bernd Lachand-Robert, Thomas Univ Cologne Inst Math D-50923 Cologne Germany Univ Savoie Lab Math F-73376 Le Bourget Du Lac France

Given a planar convex domain Omega, its Cheeger set l(Omega) is defined as the unique minimizer of vertical bar partial derivative X vertical bar/vertical bar X vertical bar among all nonempty open and simply connected subsets X of Omega. We prove an interesting geometric property of l(Omega), characterize domains Omega which coincide with l(Omega) and provide a constructive algorithm for the determination of l(Omega).

关键词： Cheeger constant Cheeger set convexity constructive algorithm connection-like coycle

来源：评论

学校读者我要写书评

暂无评论

Evolutionary strategy for learning multiple-valued logic functions

引用

JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING 2006年第5-6期12卷 459-489页

作者： Ngom, Alioune Simovici, Dan A. Stojmenovic, Ivan Univ Windsor Dept Comp Sci Windsor ON N9B 3P4 Canada Univ Massachusetts Dept Math & Comp Sci Boston MA 02125 USA Univ Ottawa Sch Informat Technol & Engn Dept Comp Sci Ottawa ON K1N 6N5 Canada

We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V subset of K-n is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

关键词： multiple-valued logic multiple-threshold perceptron evolution strategy neural network partitioning method constructive algorithm

来源：评论

学校读者我要写书评

暂无评论

A constructive algorithm for feedforward neural networks with incremental training

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2002年第12期49卷 1876-1879页

作者： Liu, DR Chang, TS Zhang, Y Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA Univ Calif Davis Dept Elect & Comp Engn Davis CA 95616 USA

We develop, in this brief, a new constructive learning algorithm for feedforward neural networks. We employ an incremental training procedure where training patterns are learned one by one. Our algorithm starts with a single training pattern and a single hidden-layer neuron. During the course of neural network training, when the algorithm gets stuck in a local minimum, we will attempt to escape from the local minimum by using the weight scaling technique. It is only after several consecutive failed attempts in escaping from a local minimum that will we allow the network to grow by adding a hidden-layer neuron. At this stage, we employ an optimization procedure based on quadratic/linear programming to select initial weights for the newly added neuron. Our optimization procedure tends to make the network reach the error tolerance with no or little training after adding a hidden-layer neuron. Our simulation results indicate that the present constructive algorithm can obtain neural networks very close to minimal structures (with the least possible number of hidden-layer neurons) and that convergence (to a solution) in neural network training can be guaranteed. We tested our algorithm extensively using a widely used benchmark problem, i.e., the parity problem.

关键词： constructive algorithm feedforward neural networks incremental training linear programming quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Evolutionary strategy for learning multiple-valued logic functions

Evolutionary strategy for learning multiple-valued logic fun...

引用

34th International Symposium on Multiple-Valued Logic (ISMVL 2004)

作者： Ngom, A Simovici, DA Stojmenovic, I Univ Windsor Dept Comp Sci Windsor ON N9B 3P4 Canada

ISBN: (纸本)0769521304

We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V subset of or equal to K-n is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

关键词： multiple-valued logic multiple-threshold perceptron evolution strategy neural network partitioning method constructive algorithm

来源：评论

学校读者我要写书评

暂无评论

Automatic synthesis of multiple place resource models with Petri nets

Automatic synthesis of multiple place resource models with P...

引用

American Control Conference

作者： Ferrarini, L Piroddi, L Politecn Milan Dipartimento Elettr & Informat I-20133 Milan Italy

ISBN: (纸本)0780383354

The paper focuses on the correct representation of shared resources in Petri net models of automated manufacturing systems, in the presence of concurrent independent operations, such as assembly and disassembly ones. In particular, an original multiple-place model is specifically derived and a constructive algorithm is proposed for the automatic synthesis of the resource model. The algorithm computes the number of resource places for each resource, as well as their connections to the recipes' transitions. Proper necessary conditions of "well-definiteness" are introduced for the partial models that are incrementally defined by the user.

关键词： manufacturing systems resource allocation Petri nets automatic synthesis multiple place resource models Petri net model resource sharing automated manufacturing systems constructive algorithm necessary condition

来源：评论

学校读者我要写书评

暂无评论

On the optimal structure design of multilayer feedforward neural networks for pattern recognition

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2002年第4期16卷 375-398页

作者： Chen, DQ Burrell, P S Bank Univ Knowledge Based Syst Ctr Sch Comp Informat Syst & Math London SE1 0AA England

In this survey paper, the-state-of-the-art of the optimal structure design of Multilayer Feedforward Neural Network (MFNN) for pattern recognition is reviewed. Special emphasis is laid on the scale-limited MFNN and the internal representation and decision boundary-based design methodologies. A comprehensively comparative study of the main characteristics of each method is presented. Also, future research directions are outlined.

关键词： multilayer feedforward neural network multilayer perceptron internal representation pruning algorithm genetic algorithm constructive algorithm discriminant decision machine learning support vector machine

来源：评论

学校读者我要写书评

暂无评论

STRIP - A strip-based neural-network growth algorithm for learning multiple-valued functions

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2001年第2期12卷 212-227页

作者： Ngom, A Stojmenovic, I Milutinovic, V Univ Windsor Dept Comp Sci Windsor ON N9B 3P4 Canada Univ Ottawa Sch Informat Technol & Engn Dept Comp Sci Ottawa ON K1N 6N5 Canada Univ Belgrade Sch Elect Engn Dept Comp Engn YU-11120 Belgrade Serbia Yugoslavia

We consider the problem of synthesizing multipIe-valued logic functions by neural networks. A genetic algorithm (GA) which finds the longest strip in V subset of or equal to K (n) is described. A strip contains points located between two parallel hyperplanes. Repeated application of GA partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct two neural networks based on these hidden units and show that they correctly compute the given but arbitrary multiple-valued function. Preliminary experimental results are presented and discussed.

关键词： constructive algorithm genetic algorithm multiple-threshold perceptron multiple-valued logic neural network partitioning

来源：评论

学校读者我要写书评

暂无评论

A new algorithm to design compact two-hidden-layer artificial neural networks

引用

NEURAL NETWORKS 2001年第9期14卷 1265-1278页

作者： Islam, MM Murase, K Univ Fukui Dept Human & Artificial Intelligence Syst Fukui 9108507 Japan

This paper describes the cascade neural network design algorithm (CNNDA), a new algorithm for designing compact, two-hidden-layer artificial neural networks (ANNs). This algorithm determines an ANN's architecture with connection weights automatically. The design strategy used in the CNNDA was intended to optimize both the generalization ability and the training time of ANNs. In order to improve the generalization ability, the CNDDA uses a combination of constructive and pruning algorithms and bounded fan-ins of the hidden nodes. A new training approach, by which the input weights of a hidden node are temporarily frozen when its output does not change much after a few successive training cycles, was used in the CNNDA for reducing the computational cost and the training time. The CNNDA was tested on several benchmarks including the cancer, diabetes and character-recognition problems in ANNs. The experimental results show that the CNNDA can produce compact ANNs with good generalization ability and short training time in comparison with other algorithms. (C) 2001 Elsevier Science Ltd. All rights reserved.

关键词： constructive algorithm pruning algorithm weight freezing generalization ability training time

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：