Robust Stability of Switched Recurrent Neural Networks with Discrete and Distributed Delays under Uncertainty

Authors:
Shiping Wen;Zhigang Zeng;Lingfa Zeng
Affiliations:
School of Automation, Wuhan University of Technology, Wuhan, China 430070;School of Automation, Wuhan University of Technology, Wuhan, China 430070;School of Automation, Wuhan University of Technology, Wuhan, China 430070
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 2
Cited 1

Understanding and using patterns in software development

Theory and Practice of Object Systems - Special issue on patterns
Global exponential stability of generalized recurrent neural networks with discrete and distributed delays

Neural Networks

Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the rapid development of intelligent control, switched systems have attracted great attention. In this letter, we try to introduce the idea of the switched systems into the field of recurrent neural networks (RNNs) with discrete and distributed delays under uncertainty which is considered to be norm bounded. At first, we establish the mathematical model of the switched RNNs in which a set of RNNs are used as the subsystems and an arbitrary switching rule is assumed. Secondly, for this kind of systems, robust analysis which is based on the Lyapunov-Krasovii approach is addressed, and for all admissible parametric uncertainties, some criteria which are derived in terms of a series of strict LMIs are presented to guarantee the switched RNNs to be globally exponentially stable. Finally, a specific example is shown to illustrate the applicability of the methodology.