PROGRESSIVE LEARNING ALGORITHM FOR GSN FEEDFORWARD NEURAL ARCHITECTURES

被引：0

作者：

DECARVALHO, A

FAIRHURST, MC

BISSET, DL

机构：

[1] Electronic Engineering Laboratories, University of Kent at Canterbury, Canterbury

来源：

ELECTRONICS LETTERS | 1994年 / 30卷 / 06期

关键词：

NEURAL NETWORKS; PATTERN RECOGNITION;

D O I：

10.1049/el:19940326

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 new learning algorithm, the progressive learning algorithm, is proposed for use in a goal-seeking feedforward architecture, GSN(f). Experiments show that both improved recognition performance and significantly faster training times can be achieved with this learning algorithm.

引用

页码：506 / 507

页数：2