DocumentCode
2990259
Title
Recurrent fuzzy neural networks for nonlinear system identification
Author
Yu, Wen ; Li, XiaoOu
Author_Institution
CINVESTAV-IPN, Mexico
fYear
2007
fDate
1-3 Oct. 2007
Firstpage
590
Lastpage
595
Abstract
In this paper, we propose a new recurrent fuzzy neural network, which has the standard state space form, we call it state-space recurrent neural networks. Input-to-state stability is applied to access robust training algorithms for system identification. Stable learning algorithms for the premise part and the consequence part of fuzzy rules are proved.
Keywords
identification; neurocontrollers; nonlinear control systems; recurrent neural nets; state-space methods; fuzzy rules; input-to-state stability; nonlinear system identification; recurrent fuzzy neural networks; robust training algorithms; Backpropagation algorithms; Fuzzy neural networks; Fuzzy systems; Neural networks; Neurofeedback; Nonlinear systems; Robustness; Stability; State-space methods; System identification;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Control, 2007. ISIC 2007. IEEE 22nd International Symposium on
Conference_Location
Singapore
ISSN
2158-9860
Print_ISBN
978-1-4244-0440-7
Electronic_ISBN
2158-9860
Type
conf
DOI
10.1109/ISIC.2007.4450952
Filename
4450952
Link To Document