Exploring the nonlinear dynamic behavior of artificial neural networks

Author

Von Zuben, Fernando J. ; De Andrade Netto, Márcio L.

Author_Institution

Sch. of Electr. Eng., State Univ. of Campinas, Brazil

Volume

2

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

1000

Abstract

This paper explores the universal approximation capability exhibited by neural networks in the development of suitable architectures and associated training processes for nonlinear discrete-time dynamic system representation. The resulting architectures include recurrent and non recurrent multilayer neural networks and the derived training processes can be seen as optimization problems. Particular attention is given to the investigation of the dynamic behavior of a recurrent processing unit

Keywords

learning (artificial intelligence); optimisation; recurrent neural nets; artificial neural networks; multilayer neural networks; nonlinear discrete-time dynamic system representation; nonlinear dynamic behavior; optimization problems; training processes; universal approximation capability; Artificial neural networks; Computer architecture; Delay effects; Ear; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonlinear dynamical systems; Recurrent neural networks; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374319

Filename

374319