Title :
Expenential stability of recurrent neural networks with time-varying discrete and distributed delays
Author :
Yonghua, Liu ; Wenguang, Luo
Author_Institution :
Dept. of Electron. Inf. & Control Eng., Guangxi Univ. of Technol., Liuzhou, China
Abstract :
The global exponential stability of a class of recurrent neural networks (RNNs) with time-varying discrete and distributed delays is investigated. A novel delay-dependent sufficient condition is derived based on Lyapunov-Krasovskii functional and the linear matrix inequality (LMI) technique, under a more general assumption on the activation function. Finally, A illustrate example is given to show the effectiveness of our theoretical result.
Keywords :
Lyapunov methods; asymptotic stability; delays; linear matrix inequalities; recurrent neural nets; Lyapunov-Krasovskii functional; activation function; delay-dependent sufficient condition; distributed delays; global exponential stability; linear matrix inequality; recurrent neural networks; time-varying discrete delays; Artificial neural networks; Asymptotic stability; Delay; Linear matrix inequalities; Stability criteria; Symmetric matrices; distributed delays; exponential stability; linear matrix inequality; recurrent neural networks; time-varying delays;
Conference_Titel :
Computer Science and Education (ICCSE), 2010 5th International Conference on
Conference_Location :
Hefei
Print_ISBN :
978-1-4244-6002-1
DOI :
10.1109/ICCSE.2010.5593676
