Adaptive training of feedback neural networks for non-linear filtering

Author

Dreyfus, G. ; Macchi, O. ; Marcos, S. ; Nerrand, O. ; Personnaz, L. ; Roussel-Ragot, P. ; Urbani, D. ; Vignat, C.

Author_Institution

Ecole Superieure de Phys. et de Chimie Ind. de la Ville de Paris, France

fYear

1992

fDate

31 Aug-2 Sep 1992

Firstpage

550

Lastpage

559

Abstract

The authors propose a general framework which encompasses the training of neural networks and the adaptation of filters. It is shown that neural networks can be considered as general nonlinear filters which can be trained adaptively, i.e., which can undergo continual training. A unified view of gradient-based training algorithms for feedback networks is proposed, which gives rise to new algorithms. The use of some of these algorithms is illustrated by examples of nonlinear adaptive filtering and process identification

Keywords

adaptive filters; learning (artificial intelligence); recurrent neural nets; adaptive filtering; adaptive training; feedback neural networks; gradient-based training algorithms; nonlinear filters; process identification; Adaptive control; Adaptive filters; Feedforward neural networks; Filtering algorithms; Industrial training; Neural networks; Neurofeedback; Neurons; Output feedback; Programmable control;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1992] II., Proceedings of the 1992 IEEE-SP Workshop

Conference_Location

Helsingoer

Print_ISBN

0-7803-0557-4

Type

conf

DOI

10.1109/NNSP.1992.253657

Filename

253657