22 March 1996 Function approximation by polynomial wavelets generated from powers of sigmoids
Author Affiliations +
Abstract
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.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joao Fernando Marar, Edson C. B. Carvalho Filho, Germano C. Vasconcelos, "Function approximation by polynomial wavelets generated from powers of sigmoids", Proc. SPIE 2762, Wavelet Applications III, (22 March 1996); doi: 10.1117/12.236043; https://doi.org/10.1117/12.236043
PROCEEDINGS
10 PAGES


SHARE
Back to Top