DocumentCode
404072
Title
Discrete-time nonlinear system identification using recurrent neural networks
Author
Yu, Wen ; Li, Xiaooi
Author_Institution
Dept. de Control Automatico, CINVESTAV-IPN, Mexico City, Mexico
Volume
4
fYear
2003
fDate
9-12 Dec. 2003
Firstpage
3996
Abstract
In this paper we proposed a novel discrete-time recurrent neural networks. Input-to-state stability (ISS) approach is applied to access robust training algorithms. We conclude that for discrete-time nonlinear system identification, the gradient descent law and the backpropagation-like algorithm for the weights adjustment are stable in the sense of L∞ and robust to any bounded uncertainties.
Keywords
backpropagation; discrete time systems; nonlinear systems; recurrent neural nets; stability; backpropagation like algorithm; bounded uncertainties; discrete time nonlinear system; gradient descent law; input-to-state stability; recurrent neural networks; system identification; training algorithms; weights adjustment; Backpropagation algorithms; Feedforward neural networks; Function approximation; Neural networks; Nonlinear systems; Recurrent neural networks; Robust stability; Robustness; Stability analysis; Uncertainty;
fLanguage
English
Publisher
ieee
Conference_Titel
Decision and Control, 2003. Proceedings. 42nd IEEE Conference on
ISSN
0191-2216
Print_ISBN
0-7803-7924-1
Type
conf
DOI
10.1109/CDC.2003.1271775
Filename
1271775
Link To Document