Title :
Almost sure adaptive synchronization for neutral-type neural networks with Markovian switching
Author :
Yang Xueqing ; Zhou Wuneng ; Yang Jun ; Dai Anding
Author_Institution :
Sch. of Inf. Sci. & Technol., Donghua Univ., Shanghai, China
Abstract :
The problem of almost sure (a. s.) adaptive synchronization for neutral-type neural networks with Markovian switching is researched in this paper. A new criterion of a. s. asymptotic stability for a general neutral-type stochastic differential equation which extends the existed results is given firstly. Next, based upon this stability criterion, by making use of Lyapunov functional method and designing a adaptive controller, a condition of a. s. asymptotic adaptive synchronization for neutral-type neural networks with stochastic perturbation and Markovian switching is obtained. The synchronization condition is expressed as linear matrix inequality which can be easily solved by Matlab. A numerical example to illustrate the effectiveness of the method and result is introduced finally.
Keywords :
Lyapunov methods; Markov processes; adaptive control; asymptotic stability; control system synthesis; differential equations; linear matrix inequalities; neurocontrollers; stochastic processes; Lyapunov functional method; Markovian switching; Matlab; adaptive controller design; asymptotic adaptive synchronization; asymptotic stability; general neutral-type stochastic differential equation; linear matrix inequality; neutral-type neural networks; stability criterion; stochastic perturbation; Adaptive systems; Asymptotic stability; Delays; Neural networks; Stochastic processes; Switches; Synchronization; Adaptive Synchronization; Linear Matrix Inequality; Markovian Switching; Neutral-Type Neural Network; Stochastic Perturbation;
Conference_Titel :
Control Conference (CCC), 2014 33rd Chinese
Conference_Location :
Nanjing
DOI :
10.1109/ChiCC.2014.6895782
