DocumentCode
2532816
Title
Passive properties of dynamic neural networks
Author
Yu, Wen ; Li, XiaoOu
Author_Institution
Dept. de Control Autom., CINVESTAV-IPN, Mexico City, Mexico
Volume
2
fYear
2000
fDate
2000
Firstpage
1445
Abstract
In this paper the passivity approach is used to access several stability properties of dynamic neural networks. By using a simple gradient learning law, the conditions for passivity, stability, asymptotic stability and input-to-state stability are established
Keywords
asymptotic stability; learning (artificial intelligence); neural nets; nonlinear systems; asymptotic stability; dynamic neural networks; gradient learning; nonlinear systems; passivity; Asymptotic stability; Circuit stability; Control systems; Error correction; Multi-layer neural network; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Stability analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
American Control Conference, 2000. Proceedings of the 2000
Conference_Location
Chicago, IL
ISSN
0743-1619
Print_ISBN
0-7803-5519-9
Type
conf
DOI
10.1109/ACC.2000.876740
Filename
876740
Link To Document