MODIFIED BACKPROPAGATION ALGORITHM FOR FAST LEARNING IN NEURAL NETWORKS

被引:10
|
作者
REYNERI, LM
FILIPPI, E
机构
[1] Dipartimento di Elettronica, Politecnico di Torino, Torino, Corso Duca degli Abruzzi, 24
关键词
Adaptive systems and control; Neural networks;
D O I
10.1049/el:19901004
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A fast learning rule for artificial neural systems which is based on modifications to a back propagation algorithm described. The rule minimises the error function along direction of the gradient and backpropagates the error pattern according to a constant error energy approach. © 1990, The Institution of Electrical Engineers. All rights reserved.
引用
收藏
页码:1564 / 1566
页数:3
相关论文
共 50 条