Approximation to continuous functionals and operators using adaptive higher-order feedforward neural networks

Author

Xu, Skuxiang ; Zhang, Ming

Author_Institution

Dept. of Comput. & Inf. Syst., Univ. of Western Sydney, Campbelltown, NSW, Australia

Volume

1

fYear

1999

fDate

1999

Firstpage

370

Abstract

The approximation capabilities of adaptive higher-order feedforward neural network (AHFNN) with neuron-adaptive activation function (NAF) to any nonlinear continuous functional and any nonlinear continuous operator are studied. Universal approximation theorems of AHFNN to continuous functionals and continuous operators are given, and learning algorithms based on the steepest descent rule are derived to tune the free parameters in NAF as well as connection weights between neurons. We apply the algorithms to approximate continuous dynamical systems

Keywords

adaptive systems; feedforward neural nets; function approximation; learning (artificial intelligence); connection weights; continuous dynamical systems; feedforward neural networks; functional approximation; learning algorithms; neuron-adaptive activation function; steepest descent rule; Approximation algorithms; Australia; Computer networks; Design engineering; Feedforward neural networks; Function approximation; Information systems; Neural networks; Neurons; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.831521

Filename

831521