Exponential stability of stochastic neural networks with time-variant mixed time-delays and uncertainty

In this paper, the global exponential stability analysis is considered for time-variant stochastic neural networks with mixed time-variant time-delays and parameter uncertainties. The delays are time-variant, and the uncertainties are norm-bounded for all of the network parameters. The purpose of th...

Full description

Saved in:
Bibliographic Details
Published in2014 9th IEEE Conference on Industrial Electronics and Applications pp. 31 - 35
Main Authors Yuqing Sun, Wuneng Zhou
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2014
Subjects
Control theory
Delays
exponential stability
linear matrix inequality
Neural networks
Robustness
Stability analysis
stochastic neural networks
time-variant time-delays
Uncertainty
Online AccessGet full text

Cover

More Information
Summary:In this paper, the global exponential stability analysis is considered for time-variant stochastic neural networks with mixed time-variant time-delays and parameter uncertainties. The delays are time-variant, and the uncertainties are norm-bounded for all of the network parameters. The purpose of this paper is to establish easily and verifiable conditions which the delays neural network is globally, robustly, exponentially stable in the mean square for all admissible parameter uncertainties. By resorting to the Lyapunov-Krasovskii stability theory and the stochastic analysis method, a linear matrix inequality (LMI) approach is developed to derive the stability required. An example is provided to demonstrate the effectiveness and applicability of the proposed criteria.
ISSN:2156-2318
2158-2297
DOI:10.1109/ICIEA.2014.6931126