A novel neural network training algorithm based on particle swarm optimizer and optimal foraging theory
Niu B(牛奔); Zhu YL(朱云龙); Hu KY(胡琨元); He XX(何小贤)
刊名DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS
2007
卷号14期号:S页码:370-375
关键词particle swarm optimization optimal foraging theory neural network
ISSN号1492-8760
通讯作者牛奔
产权排序1
中文摘要A novel neural network training algorithm based on particle swarm optimization (PSO) and optimal foraging theory (OFT) is presented in this paper. The proposed algorithm, called PSOOFT, makes use of two mechanisms of OFT: a reproduction strategy to enhance the ability to converge rapidly to good solutions and a patch-choice based scheme to keep a right balance of exploration, and exploitation, The PSOOFT is applied for training a multi-layer feed-forward neural network for three benchmark classification problems. The performance of PSOOFT used for neural network training is compared to that of Back Propagation (BP), genetic algorithm (GA) and standard PSO (SPSO), demonstrating its effectiveness and efficiency.
收录类别CPCI(ISTP)
语种英语
WOS记录号WOS:000252392000061
公开日期2012-05-29
内容类型期刊论文
源URL[http://ir.sia.cn/handle/173321/6871]  
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 novel neural network training algorithm based on particle swarm optimizer and optimal foraging theory[J]. DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS,2007,14(S):370-375.
APA Niu B,Zhu YL,Hu KY,&He XX.(2007).A novel neural network training algorithm based on particle swarm optimizer and optimal foraging theory.DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS,14(S),370-375.
MLA Niu B,et al."A novel neural network training algorithm based on particle swarm optimizer and optimal foraging theory".DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS 14.S(2007):370-375.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace