The multidimensional function approximation based on constructive wavelet RBF neural network

For the multidimensional continuous function, using constructive feedforward wavelet RBF neural network, we prove that a wavelet RBF neural network with n + 1 hidden neurons can interpolate n + 1 multidimensional samples with zero error. Then we prove they can uniformly approximate any continuous mu...

Full description

Saved in:
Bibliographic Details
Published inApplied soft computing Vol. 11; no. 2; pp. 2173 - 2177
Main Authors Muzhou, Hou, Xuli, Han
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.03.2011
Subjects
Interpolate
Uniformly approximation
Wavelet RBF neural networks
Wavelet RBF neural networks
Uniformly approximation
Interpolate
Online AccessGet full text

Cover

More Information
Summary:For the multidimensional continuous function, using constructive feedforward wavelet RBF neural network, we prove that a wavelet RBF neural network with n + 1 hidden neurons can interpolate n + 1 multidimensional samples with zero error. Then we prove they can uniformly approximate any continuous multidimensional function with arbitrary precision. This method can avoid the defects of conventional neural networks using learning algorithm in practice. The correctness and effectiveness are verified through four numeric experiments.
ISSN:1568-4946
1872-9681
DOI:10.1016/j.asoc.2010.07.016