A Cooperative Evolutionary System for Designing Neural Networks

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 工业信息学研究室 > 先进制造技术研究室

	A Cooperative Evolutionary System for Designing Neural Networks
	Niu B(牛奔); Zhu YL(朱云龙); Hu KY(胡琨元); Li SF(李素粉); He XX(何小贤)
	2006
会议名称	International Conference on Intelligent Computing (ICIC)
会议日期	August 16-19, 2006
会议地点	Kunming, China
页码	12-21
中文摘要	A novel cooperative evolutionary system, i.e., CGPNN, for automatic design artificial neural networks (ANN's) is presented where ANN's structure and parameters are tuned simultaneously. The algorithms used in CGPNN combine genetic algorithm (GA) and particle swarm optimization (PSO) on the basis of a direct encoding scheme. In CGPNN, standard (real-coded) PSO is employed to training ANN's free parameters (weights and bias) and binary-coded GA is used to find optimal ANN's structure. In the simulation part, CGPNN is applied to the predication of tool life. The experimental results show that CGPNN has good accuracy and generalization ability in comparison with other algorithms.
收录类别	EI ; CPCI（ISTP）
产权排序	1
会议主办者	IEEE Computat Intelligence Soc, Int Neural Network Soc, Natl Sci Fdn China
会议录	INTELLIGENT COMPUTING, PART I - INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING, ICIC 2006, PART I
会议录出版者	SPRINGER-VERLAG
会议录出版地	BERLIN
语种	英语
ISSN号	0302-9743
ISBN号	978-3-540-37271-4
WOS记录号	WOS:000278727500002
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/8153]
专题	沈阳自动化研究所_工业信息学研究室_先进制造技术研究室
推荐引用方式 GB/T 7714	Niu B,Zhu YL,Hu KY,et al. A Cooperative Evolutionary System for Designing Neural Networks[C]. 见:International Conference on Intelligent Computing (ICIC). Kunming, China. August 16-19, 2006.