首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Convergence of gradient method for Elman networks
Authors:Wei Wu  Dong-po Xu  Zheng-xue Li
Institution:Department of Applied Mathematics,Dalian University of Technology,Dalian 116024,Liaoning Province,P.R.China
Abstract:The gradient method for training Elman networks with a finite training sample set is considered.Monotonicity of the error function in the iteration is shown.Weak and strong convergence results are proved,indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point,respectively.A numerical example is given to support the theoretical findings.
Keywords:Elman network  gradient learning algorithm  convergence  monotonicity
本文献已被 维普 万方数据 SpringerLink 等数据库收录!
点击此处可从《应用数学和力学(英文版)》浏览原始摘要信息
点击此处可从《应用数学和力学(英文版)》下载免费的PDF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