Function Approximation by Polynomial Wavelets Generated

Wavelet functions have been successfully used in many problems as the activation function of feedforward neural networks ZB92],,STK92], PK93]. In this paper, a family of polynomial wavelets generated from powers of sigmoids is described which provides a robust way for designing neural network architectures. It is shown, through experimentation, that function members of this family can present a very good adaptation capability which make them attractive for applications of function approximation. In the experiments carried out, it is observed that only a small number of daughter wavelets is usually necessary to provide good approximation characteristics.