Wavelet networks

A wavelet network concept, which is based on wavelet transform theory, is proposed as an alternative to feedforward neural networks for approximating arbitrary nonlinear functions. The basic idea is to replace the neurons by ;wavelons', i.e., computing units obtained by cascading an affine transform and a multidimensional wavelet. Then these affine transforms and the synaptic weights must be identified from possibly noise corrupted input/output data. An algorithm of backpropagation type is proposed for wavelet network training, and experimental results are reported.

[1]  A. Grossmann,et al.  DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE , 1984 .

[2]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[3]  I. Daubechies,et al.  PAINLESS NONORTHOGONAL EXPANSIONS , 1986 .

[4]  B. Philippe.  An algorithm to improve nearly orthonormal sets of vectors on a vector processor , 1987 .

[5]  I. Daubechies.  Orthonormal bases of compactly supported wavelets , 1988 .

[6]  R. Hecht-Nielsen,et al.  Back propagation error surfaces can have local minima , 1989, International 1989 Joint Conference on Neural Networks.

[7]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[8]  S. M. Carroll,et al.  Construction of neural nets using the radon transform , 1989, International 1989 Joint Conference on Neural Networks.

[9]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[11]  S. Mallat.  Multiresolution approximations and wavelet orthonormal bases of L^2(R) , 1989 .

[12]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[13]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[14]  P. Burrascano,et al.  A learning rule eliminating local minima in multilayer perceptrons , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[15]  L. Jones.  Constructive approximations for neural networks by sigmoidal functions , 1990, Proc. IEEE.

[16]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[17]  Rama Chellappa,et al.  A unified approach to boundary perception: edges, textures, and illusory contours , 1993, IEEE Trans. Neural Networks.

[18]  Yagyensh C. Pati,et al.  Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations , 1993, IEEE Trans. Neural Networks.