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

共 22 条

[1]

BARRON AR, 1991, IN PRESS IEEE T INFO

[2]

BENVENISTE A, 1990, APPLICATIONS MATH, V22

[3]

BURRASCANO P, 1990, APR P ICASSP 90 ALB

[4]

Carrol S.M., 1989, P IJCNN

[5]

Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274

[6] ORTHONORMAL BASES OF COMPACTLY SUPPORTED WAVELETS [J].

DAUBECHIES, I .

COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS, 1988, 41 (07) :909-996

[7] PAINLESS NONORTHOGONAL EXPANSIONS [J].

DAUBECHIES, I ;

GROSSMANN, A ;

MEYER, Y .

JOURNAL OF MATHEMATICAL PHYSICS, 1986, 27 (05) :1271-1283

[8]

DAUBECHIES I, 1990, IEEE T INFORMAT THEO, V36

[9] DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE [J].

GROSSMANN, A ;

MORLET, J .

SIAM JOURNAL ON MATHEMATICAL ANALYSIS, 1984, 15 (04) :723-736

[10]

HANNAN EJ, 1988, STATISTICAL THEORY L

← 1 2 3 →