Discrete Affine Wavelet Transforms for Anaylsis and Synthesis of Feedfoward Neural Networks
Abstract
In this paper we show that discrete affine wavelet transforms can provide a tool for the analysis and synthesis of standard feedforward neural net(cid:173) works. It is shown that wavelet frames for L2(IR) can be constructed based upon sigmoids. The spatia-spectral localization property of wavelets can be exploited in defining the topology and determining the weights of a feedforward network. Training a network constructed using the synthe(cid:173) sis procedure described here involves minimization of a convex cost func(cid:173) tional and therefore avoids pitfalls inherent in standard backpropagation algorithms. Extension of these methods to L2(IRN) is also discussed.
Cite
Text
Pati and Krishnaprasad. "Discrete Affine Wavelet Transforms for Anaylsis and Synthesis of Feedfoward Neural Networks." Neural Information Processing Systems, 1990.Markdown
[Pati and Krishnaprasad. "Discrete Affine Wavelet Transforms for Anaylsis and Synthesis of Feedfoward Neural Networks." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/pati1990neurips-discrete/)BibTeX
@inproceedings{pati1990neurips-discrete,
title = {{Discrete Affine Wavelet Transforms for Anaylsis and Synthesis of Feedfoward Neural Networks}},
author = {Pati, Y. C. and Krishnaprasad, P. S.},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {743-749},
url = {https://mlanthology.org/neurips/1990/pati1990neurips-discrete/}
}