Almost surely asymptotic synchronization for stochastic neural networks of neutral type with Markovian jumping parameters

Abstract

This paper studies the problem of the almost surely asymptotic synchronization for a class of stochastic neural networks of neutral type with both Markovian jumping parameters and mixed time delays. Based on the stochastic analysis theory, LaSalle-type invariance principle, and delayed state-feedback control technique, some novel delay-dependent sufficient criteria to guarantee the almost surely asymptotic synchronization are given. These criteria are expressed as the linear matrix inequalities, which can be easily checked by MATLAB LMI Control Toolbox. Finally, four numerical examples and their simulations are provided to illustrate the effectiveness of the proposed method. KEYWORDS almost surely asymptotic synchronization, LaSalle invariant principle, Markovian jumping parameters, state-feedback control, stochastic neural network, time-varying delay 1524

Observer‐based guaranteed cost control for IT‐2 stochastic fuzzy coupled neural networks with Markov switching topology

“…Remark It should be noted that so far in the literature, a lots of studies has been reported concerning synchronization of NNs, for instance, see References 9, 14‐17, 28, and 32. Nevertheless, only very few papers have been focused on the issue of synchronization of SNNs with coupling configuration 12,17,18 .…”

“…Hence, the stability of stochastic neural networks (SNNs) has attained persistent attention among the research communities. In recent years, vast quantity of significant results on SNNs with time‐varying delays have been discussed (see, for instance, References 9‐14). Particularly, the authors in Reference 9 inspected the finite‐time synchronization problem for a class of nonlinear SNNs subject to time‐delay and noise disturbance.…”

Passive state estimation for Markov jumping inertial neural networks under fading channels

“…Furthermore, NNs usually exhibit the characteristics of network modes jumping and such jumping general are regarded as to be decided by the homogeneous Markov chain in the majority of results. [11][12][13][14][15][16][17][18][19][20][21] By taking this fact into account, enormous works related to the Markov jumping NNs (MJNNs) have been published recently. For example, the authors in Reference 22 investigated observer-based sliding mode control for Markov jump systems with actuator failures and asynchronous modes, and the issue of the asynchronous mean stabilization of jump systems with piecewise-homogeneous Markov chain was explored in Reference 23.…”

“…It is worth remarking that due to the possible occurrence of sudden environmental disturbances or component failures in the actual engineering, the structure and parameters of NNs may undergo an unknown abrupt change, which may lead the degradation of the system performance or even instability. Furthermore, NNs usually exhibit the characteristics of network modes jumping and such jumping general are regarded as to be decided by the homogeneous Markov chain in the majority of results 11‐21 . By taking this fact into account, enormous works related to the Markov jumping NNs (MJNNs) have been published recently.…”