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.
This work was supported by the National Science Foundation of China (Grant No.60375021) and the Science Foundation of Hunan Province (Grant No.00JJY3096) and the Key Project of Hunan Provincial Education Department (Grant No.04A056)
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Zhang, Q., Benveniste, A.: Wavelet network. IEEE Trans. on NN 3, 889–898 (1992)
Zhang, J. (ed.): Wavelet neural networks for function learning. IEEE Trans. on SP 6, 1485–1497 (1995)
Pati, Y.C., Krishnaprasad, P.S.: Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations. IEEE Trans Neural Networks 4, 73–85 (1993)
En-Bing, L., Yi, L.: 2-D nonseparable scaling function interpolation and approximation. Acta Math. Sci. 22, 19–31 (2002)
Gao, X.P., Zhang, B.: Interval-wavelets neural networks (1)—theory and implements. Journal of software 9, 217–221 (1998)
Gao, X.P., Zhang, B.: Interval-wavelets Neural Networks (II)—Properties and Experiment. Journal of software 9, 246–250 (1998)
Belogay, E., Wang, Y.: Arbitrarily smooth orthogonal non-separable wavelets in R2. SIAM J. Math. Anal. 3, 678–697 (1999)
He, W., Lai, M.J.: Examples of bivariate nonseparable compactly supported orthonormal continuous wavelets. IEEE Trans. Image Processing 9, 949–953 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, J., Gao, X., Cao, C., Xiao, F. (2005). A Fast Nonseparable Wavelet Neural Network for Function Approximation. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3610. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539087_104
Download citation
DOI: https://doi.org/10.1007/11539087_104
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28323-2
Online ISBN: 978-3-540-31853-8
eBook Packages: Computer ScienceComputer Science (R0)