首页 | 本学科首页   官方微博 | 高级检索  
     

基于遗忘进化规划的Hopfield网学习算法
引用本文:孟祥武,程 虎.基于遗忘进化规划的Hopfield网学习算法[J].软件学报,1998,9(2):151-155.
作者姓名:孟祥武  程 虎
作者单位:北京邮电大学计算机工程系,北京,100876;中国科学院软件研究所 北京 100080;中国科学院软件研究所 北京 100080
摘    要:本文提出了一个基于遗忘进化规划的Hopfield网学习算法.通过遗忘部分个体,算法能避免局部最小.给定不动点、极限环或迭代序列,通过解不等式,算法能同时获得Hopfield网的拓扑结构和权值.该算法克服了进化Hopfield网学习的局限性.它还能找到多个优化解.实验也证明了该算法的有效性.

关 键 词:进化规划  进化算法  Hopfield网  遗忘  学习算法.
收稿时间:1996/12/10 0:00:00
修稿时间:1997/4/11 0:00:00

A Learning Algorithm of Hopfield Neural Network Based on Evolutionary Programming with Forgetting
MENG Xiang-wu and MENG Xiang-wu.A Learning Algorithm of Hopfield Neural Network Based on Evolutionary Programming with Forgetting[J].Journal of Software,1998,9(2):151-155.
Authors:MENG Xiang-wu and MENG Xiang-wu
Abstract:This paper presents a learning algorithm of Hopfield neural network based on evolutionary programming with forgetting. The algorithm can avoid local minima by forgetting some individuals. Under constraints of fixed points, limit cycles or iteration sequences, the algorithm simultaneously acquires both the topology and weights for Hopfield neural network by solving inequalities. It copes with the limitations of evolving Hopfield learning algorithm. It can also find several optimal solutions. The experimental results also demonstrate the effectiveness of the algorithm.
Keywords:Evolutionary programming  evolutionary algorithm  Hopfield neural network  forgetting  learning algorithm  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号