Y. Pati, P. Krishnaprasad
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.