中立型Markov脉冲神经网络的随机稳定性

Stochastic Stability of Neutral-Type Impulsive Neural Networks with Mixed Time-Delays and Markovian Jumping Parameters

研究了含离散与无穷分布时变时滞的中立型Markov脉冲神经网络均方意义下的随机渐近稳定性.基于Lyapunov-Krasovskii泛函方法,利用推广的Jensen积分不等式、二次凸组合和倒凸组合技术,建立了新颖的稳定性条件.所得判据以线性矩阵不等式形式表示,可以通过标准Matlab软件验证.

The asymptotic stability for neutral-type neural networks with discrete and unbounded distributed time-varying delays and Markovian jumping parameters under impulsive perturbations in the mean squareis discusses.By using generalized Jensen integral inequalities,quadratic convex combination and reciprocal convex technique,a novel sufficient condition is proposed based on the Lyapunov-Krasovskii functional method to justify the asymptotic stability of the considered impulsive Markovian neural networks in the mean square.The obtained resultsformed as linear matrix inequalities can be easily verified via standard Matlab software.