Title :
LMI conditions for exponential stability of neural networks with time-varying delays
Author :
Yang, Haifeng ; Chu, Tianguang ; Zhang, Cishen
Author_Institution :
Dept. of Mech. & Eng. Sci., Peking Univ., Beijing, China
Abstract :
This paper presents sufficient conditions for global asymptotic/exponential stability of neural networks with time-varying delays. By using appropriate Lyapunov-Krasovskii functionals, we derive stability conditions in terms of linear matrix inequalities (LMIs). This is convenient for numerically checking the system stability using the powerful MATLAB LMI Toolbox. Compared with some earlier work, our result does not require any restriction on the derivative of the delay function. Numerical example shows the efficiency and less conservatism of the present result.
Keywords :
asymptotic stability; delays; linear matrix inequalities; neural nets; time-varying systems; Lyapunov-Krasovskii functionals; asymptotic stability; exponential stability; linear matrix inequalities; neural networks; time-varying delays; Asymptotic stability; Delay effects; Image processing; Linear matrix inequalities; MATLAB; Mathematical model; Neural networks; Neurons; Sufficient conditions; Switching circuits;
Conference_Titel :
Control and Automation, 2005. ICCA '05. International Conference on
Print_ISBN :
0-7803-9137-3
DOI :
10.1109/ICCA.2005.1528184
