The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
A NEW ON-LINE RECURSIVE LEARNING ALGORITHM FOR RECURRENT NEURAL NETWORK
Author(s): 
Pages: 616-621
Year: Issue:  5
Journal: ACTA AUTOMATICA SINICA

Keyword:  回归神经网络在线学习快速算法;
Abstract: 针对回归神经网络BP学习算法收敛慢的缺陷,提出了一种新的快速在线递推学习算法.本算法在目标函数中引入了遗忘因子,并借助于非线性系统的最大似然估计原理成功地解决了动态非线性系统回归神经网络模型权系数学习的实时性和快速性问题.仿真结果表明,该算法比传统的回归BP学习算法具有更快的收敛速度..
Related Articles
loading...