An adaptive higher-order neural networks (AHONN) and its approximation capabilities

Author

Xu, Shuxiang ; Zhang, Ming

Author_Institution

Sch. of Comput., Tasmania Univ., Hobart, Tas., Australia

Volume

2

fYear

2002

fDate

18-22 Nov. 2002

Firstpage

848

Abstract

The approximation capabilities of an adaptive higher-order neural network (AHONN) with a neuron-adaptive activation function (NAF) to any nonlinear continuous functional and any nonlinear continuous operator are studied. Universal approximation theorems of AHONN to continuous functionals and continuous operators are given, and learning algorithms 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 (operators).

Keywords

adaptive systems; function approximation; learning (artificial intelligence); neural nets; AHONN; adaptive higher-order neural networks; approximation capabilities; connection weights; continuous dynamical systems; free parameters; learning algorithms; neuron-adaptive activation function; nonlinear continuous functional operator; universal approximation theorems; Adaptive systems; Approximation algorithms; Australia; Computer architecture; Computer networks; Electronic mail; Feedforward neural networks; Function approximation; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on

Print_ISBN

981-04-7524-1

Type

conf

DOI

10.1109/ICONIP.2002.1198179

Filename

1198179