State-Dependent Switching Rules Design With Convergence Rate Constraint for Switched Stochastic Neural Networks

This study examines the state-dependent stabilization problem for switched stochastic neural networks (SSNNs) with convergence rate constraint. First, a novel state-dependent switching (SDS) rules is designed for SSNNs using interval stability theory, Lyapunov function method and convex combination technique, which can effectively regulate the rate of the system approaching the stable state. Subsequently, some sufficient conditions are derived to guarantee the mean-square asymptotical interval stability for the SSNNs by using this new SDS method. The results show that by applying the designed new SDS rules, the stability of the SSNNs can be achieved even if it is composed of all unstable subnetworks, and the convergence rate of the system can be regulated. Finally, the effectiveness of the proposed technique is verified through a numerical example and resistor-capacitor (RC) network circuits.