WAVELET NETWORKS

被引：1505

作者：

ZHANG, QG ^{[1
]}

BENVENISTE, A ^{[1
]}

机构：

[1] INST NATL RECH INFORMAT & AUTOMAT,INST RECH INFORMAT & SYST ALEATOIRES,F-35042 RENNES,FRANCE

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1992年 / 3卷 / 06期

关键词：

Computational methods - Mathematical transformations;

D O I：

10.1109/72.165591

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Based on the wavelet transform theory, the new notion of wavelet network is proposed as an alternative to feed-forward neural networks for approximating arbitrary nonlinear functions. An algorithm of backpropagation type is proposed for wavelet network training and experimental results are reported.

引用

页码：889 / 898

页数：10