Mean square delay dependent-probability-distribution stability analysis of neutral type stochastic neural networks

- This paper investigates the mean square delay dependent - probability - distribution stability.
- New Lyapunov-Krasovskii functional and stochastic analysis approach are used.
- A novel sufficient condition is obtained in the form of linear matrix inequality.
- Asymptotically stable in the mean-square sense is obtained for all admissible uncertainties.
- Numerical examples are given to show the effectiveness of the proposed method.

The aim of this manuscript is to investigate the mean square delay dependent-probability-distribution stability analysis of neutral type stochastic neural networks with time-delays. The time-delays are assumed to be interval time-varying and randomly occurring. Based on the new Lyapunov-Krasovskii functional and stochastic analysis approach, a novel sufficient condition is obtained in the form of linear matrix inequality such that the delayed stochastic neural networks are globally robustly asymptotically stable in the mean-square sense for all admissible uncertainties. Finally, the derived theoretical results are validated through numerical examples in which maximum allowable upper bounds are calculated for different lower bounds of time-delay.