首页 | 官方网站   微博 | 高级检索  
     

BP网络的PID型二阶快速学习算法
引用本文:邓志东,孙增圻,刘建伟.BP网络的PID型二阶快速学习算法[J].自动化学报,1995,21(1):67-72.
作者姓名:邓志东  孙增圻  刘建伟
作者单位:1.清华大学计算机系,北京;
摘    要:本文利用PID控制的思想,提出了BP网络的一种二阶快速学习算法,给出了学习因子选择的必要条件与较佳区域,并结合一非线性正弦函数进行了仿真研究.结果表明,较之标标准BP学习算法,利用此法可使学习收敛速度提高22倍左右.

关 键 词:BP网络    PID控制    快速学习算法
收稿时间:1992-12-2

Second Order Fast Learning Algorithm of BP Neural Network Via PID Control
Deng Zhidong,Sun Zengqi,Liu Jianwei.Second Order Fast Learning Algorithm of BP Neural Network Via PID Control[J].Acta Automatica Sinica,1995,21(1):67-72.
Authors:Deng Zhidong  Sun Zengqi  Liu Jianwei
Affiliation:1.Dept. of Computer Sci.&Tech.,Tsinghua University Beijing;Dept.of Control Engineering,Harbin Institute of Technology Harbin
Abstract:In this paper a second order fast learning algorithm of BP neural network,based on PID concepts, is proposed and a necessary condition and a good convergence region of learning parameter are derived. An example of nonlinear sine function is illustrated by simulation, which shows that the learning speed of the procedure described here is at least increased by 22 times more than the standard BP algorithm.
Keywords:BP neural network  PID control  fast learning algorithm  
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》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-23

京公网安备 11010802026262号