IMPROVING THE COUNTERPROPAGATION NETWORK PERFORMANCES

被引：1

作者：

CHIUDERI, A ^{[1
]}

机构：

[1] UNIV FLORENCE,DEPT ELECTR ENGN,I-50139 FLORENCE,ITALY

来源：

NEURAL PROCESSING LETTERS | 1995年 / 2卷 / 02期

关键词：

D O I：

10.1007/BF02312353

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper deals with the problem of how input data normalization can affect the performances of the Counterpropagation neural network. In the following, an example drawn from the landcover classification of remotely sensed images is presented and a solution, based on the Decorrelation Stretching technique, is proposed.

引用

页码：27 / 30

页数：4