Stability criteria for stochastic neural networks with unstable subnetworks under mixed switchings

In this paper, stability of a class of stochastic neural networks with switching signal is studied. Firstly, by means of the method of limiting average dwell time, we analyze the stability of switched systems which potentially contain unstable subsystems and stable subsystems simultaneously. Moreover, considering two types of switchings: stabilizing switchings and destabilizing switchings, we adopt time-dependent parameters to give a description of the relationship between two successive activated subsystems. Based on the obtained results for switched systems, some stability criteria for switched neural networks with stochastic disturbances are derived. At last, we present a numerical example to demonstrate the effectiveness of our results. (c) 2020 Published by Elsevier B.V.

Automated summary

This paper investigates the stability of a class of stochastic neural networks with switching signal by analyzing switched systems with potentially unstable subsystems and stable subsystems using the method of limiting average dwell time. By considering stabilizing and destabilizing switchings, the relationship between two successive activated subsystems is described with time-dependent parameters. The obtained results provide stability criteria for switched neural networks with stochastic disturbances, and a numerical example is presented to demonstrate the effectiveness of the results.