Supervised training technique for radial basis function neural networks

被引：13

作者：

Bruzzone, L ^{[1
]}

Prieto, DF ^{[1
]}

机构：

[1] Univ Genoa, Dept Biophys & Elect Engn, I-16145 Genoa, Italy

来源：

ELECTRONICS LETTERS | 1998年 / 34卷 / 11期

关键词：

D O I：

10.1049/el:19980789

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 supervised technique for training classifiers based on radial basis function (RBF) neural networks is presented. Unlike traditional techniques, this considers the class-membership of training samples to select the centres and widths of the kernel functions associated with the hidden units of an RBF network. Experiments carried out to solve an industrial visual inspection problem confirmed the effectiveness of the proposed technique.

引用

页码：1115 / 1116

页数：2