Stochastic stabilization of hybrid neural networks by periodically intermittent control based on discrete-time state observations

This paper is concerned with stabilization of hybrid neural networks by intermittent control based on continuous or discrete-time state observations. By means of exponential martingale inequality and the ergodic property of the Markov chain, we establish a sufficient stability criterion on hybrid neural networks by intermittent control based on continuous-time state observations. Meantime, by M-matrix theory and comparison method, we show that hybrid neural networks can be stabilized by intermittent control based on discrete-time state observations. Finally, two examples are presented to illustrate our theory. (c) 2023 Elsevier Ltd. All rights reserved.

Automated summary

This paper investigates the stabilization of hybrid neural networks using intermittent control based on continuous or discrete-time state observations. The stability criterion for hybrid neural networks under intermittent control with continuous-time state observations is established using exponential martingale inequality and the ergodic property of Markov chains. Furthermore, it is shown that hybrid neural networks can be stabilized by intermittent control based on discrete-time state observations using M-matrix theory and the comparison method. Two examples are provided to illustrate the theory.