Learning laws with exponential error convergence for recurrent neural networks

Author

Kosmatopoulos, Elias B. ; Christdoulou, M.A. ; Ioannou, Peters A.

Author_Institution

Dept. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece

fYear

1993

fDate

15-17 Dec 1993

Firstpage

2810

Abstract

In this paper, we propose new learning laws for adjusting the weights of recurrent high order neural networks (RHONN) when they are used to system identification problems. The main advantages of these learning laws over the classical robust adaptive ones, is that the identification error converges to zero exponentially fast, and that such a convergence is independent of the number of high order connections of the RHONN

Keywords

convergence of numerical methods; error analysis; identification; learning (artificial intelligence); nonlinear systems; recurrent neural nets; exponential error convergence; learning laws; nonlinear systems; recurrent neural networks; system identification; Adaptive algorithm; Adaptive control; Convergence; Lyapunov method; Neural networks; Neurons; Parameter estimation; Programmable control; Recurrent neural networks; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 1993., Proceedings of the 32nd IEEE Conference on

Conference_Location

San Antonio, TX

Print_ISBN

0-7803-1298-8

Type

conf

DOI

10.1109/CDC.1993.325707

Filename

325707

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2109758