Title :
Improved global asymptotic stability criteria for discrete-time stochastic neural networks with mixed time delays
Author :
Geng, Lijie ; Xu, Rui ; Li, Zhe
Author_Institution :
Inst. of Appl. Math., Shijiazhuang Mech. Eng. Coll., Shijiazhuang, China
Abstract :
This paper is concerned with the stability analysis problem for a class of discrete-time stochastic recurrent neural networks with mixed time delays. Based on the delay partitioning idea, a novel Lyapunov-Krasvskii functional is introduced. A new stability criterion is obtained by utilizing a free-weighting matrix method and some inequalities, which is characterized in terms of linear matrix inequalities (LMIs).
Keywords :
Lyapunov methods; asymptotic stability; delay systems; discrete time systems; linear matrix inequalities; recurrent neural nets; stochastic processes; LMI; Lyapunov-Krasvskii functional; delay partitioning idea; discrete-time system; free-weighting matrix method; global asymptotic stability; linear matrix inequalities; mixed time delays; stochastic recurrent neural network; Asymptotic stability; delay partitioning; discrete-time neural networks; mixed time-delays;
Conference_Titel :
Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSQRWC), 2011
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-9792-8
DOI :
10.1109/CSQRWC.2011.6037171
