Transformation of back-propagation networks in multiresolution learning

We proposed to train a backpropagation network using the multiresolution learning method. We first train a backpropagation network with input at a coarsest resolution, then gradually refine the input into finer resolution. The problem is to transform the connection weights of the backpropagation network from a coarsest level into a finest level. The objective of it is to improve the convergence rate of the networks. We evaluate two schemes for this network transformation. One is the wavelet approach and the other is the average splitting approach. Experimental results demonstrated the ability of this approach.<<ETX>>

[1]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[2]  T. Y. Young,et al.  A multiresolution approach to texture segmentation using neural networks , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[3]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[4]  Raymond L. Watrous.  Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization , 1988 .

[5]  D. R. Hush,et al.  Improving the learning rate of back-propagation with the gradient reuse algorithm , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  Gilbert Strang,et al.  Wavelets and Dilation Equations: A Brief Introduction , 1989, SIAM Rev..

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

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

[9]  I. G. BONNER CLAPPISON.  Editor , 1960, The Electric Power Engineering Handbook - Five Volume Set.

[10]  Amar Mitiche,et al.  Modeling and classification of shape using a Kohonen associative memory with selective multiresolution , 1993, Neural Networks.

[11]  S. W. Ellacott,et al.  A multiresolution neural network classifier for machine vision , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

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

[13]  Stéphane Mallat,et al.  Multifrequency channel decompositions of images and wavelet models , 1989, IEEE Trans. Acoust. Speech Signal Process..

[14]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.