CONSTRUCTION OF NEURAL NETWORKS TO APPROXIMATE ARBITRARY CONTINUOUS-FUNCTIONS OF ONE VARIABLE

被引：7

作者：

CHOI, CH ^{[1
]}

CHOI, JY ^{[1
]}

机构：

[1] SEOUL NATL UNIV,ASRI,SEOUL 151,SOUTH KOREA

来源：

ELECTRONICS LETTERS | 1992年 / 28卷 / 02期

关键词：

NEURAL NETWORKS;

D O I：

10.1049/el:19920094

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 novel method is introduced for determining the connection weights of three layer neural networks which approximate any continuous functions of one variable. The derived formulas to calculate the weights explain the roles of hidden neurons and connection weights of three layer neural networks. It is demonstrated, by examples, that this method yields an easy and efficient construction of neural networks without needing training to approximate a function of one variable.

引用

页码：151 / 153

页数：3