NONLINEAR PARAMETER-ESTIMATION VIA THE GENETIC ALGORITHM

Authors
YAO L SETHARES WA
Citation
L. Yao et Wa. Sethares, NONLINEAR PARAMETER-ESTIMATION VIA THE GENETIC ALGORITHM, IEEE transactions on signal processing, 42(4), 1994, pp. 927-935
Citations number
27
Categorie Soggetti
Acoustics
Journal title
IEEE transactions on signal processing → ACNP
ISSN journal
1053587X
Volume
42
Issue
4
Year of publication
1994
Pages
927 - 935
Database
ISI
SICI code
1053-587X(1994)42:4<927:NPVTGA>2.0.ZU;2-T
Abstract
A modified genetic algorithm is used to solve the parameter identifica tion problem for linear and nonlinear digital filters. Under suitable hypotheses, the estimation error is shown to converge in probability t o zero. The scheme is also applied to feedforward and recurrent neural networks.