On-line training and pruning for recursive least square algorithms

被引：37

作者：

Leung, CS ^{[1
]}

Wong, KW ^{[1
]}

Sum, PF ^{[1
]}

Chan, LW ^{[1
]}

机构：

[1] CITY UNIV HONG KONG,DEPT ELECT ENGN,KOWLOON,HONG KONG

来源：

ELECTRONICS LETTERS | 1996年 / 32卷 / 23期

关键词：

neural networks; least squares approximations;

D O I：

10.1049/el:19961443

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：

The authors derive a pruning method for recursive least square (RLS) based algorithms. In this approach, training (on-line type) and pruning are combined. Simulation results showed that this approach is an effective training and pruning method for neural networks.

引用

页码：2152 / 2153

页数：2