A fast nonseparable wavelet neural network for function approximation

Authors:
Jun Zhang;Xieping Gao;Chunhong Cao;Fen Xiao
Affiliations:
Member, IEEE Information Engineering College, Xiangtan University, China;Member, IEEE Information Engineering College, Xiangtan University, China;Member, IEEE Information Engineering College, Xiangtan University, China;Member, IEEE Information Engineering College, Xiangtan University, China
Venue:
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Year:
2005

Citing 3
Cited 0

Arbitrarily smooth orthogonal nonseparable wavelets in R2

SIAM Journal on Mathematical Analysis
Wavelet neural networks for function learning

IEEE Transactions on Signal Processing
Examples of bivariate nonseparable compactly supported orthonormal continuous wavelets

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, based on the theory of nonseparable wavelet, a novel nonseparable wavelet model has been proposed. The structure of the model is distinguished from that of wavelet network (RBF structure). It is a four-layer structure, which helps overcome the structural redundancy. In the process of the training of the network, in the light of the characteristics of nonseparable wavelet, a novel method of setting the initial value of weight has been proposed. It can overcome the shortcoming of gradient descent methodology that it makes the convergence of the network slow. Some experiments with the novel model for function learning will be shown. Comparing with the present wavelet networks, BP network, the results in this paper show that the speed and generalization performance of the novel model have been greatly improved.