Exponentially convergent state estimation for delayed switched recurrent neural networks
Seoul National University of Science & Technology, 172 Gongneung 2-dong, Nowon-gu, 139-743, Seoul, Korea
* e-mail: firstname.lastname@example.org
Accepted: 30 September 2011
Published online: 21 November 2011
This paper deals with the delay-dependent exponentially convergent state estimation problem for delayed switched neural networks. A set of delay-dependent criteria is derived under which the resulting estimation error system is exponentially stable. It is shown that the gain matrix of the proposed state estimator is characterised in terms of the solution to a set of linear matrix inequalities (LMIs), which can be checked readily by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed state estimator.
© EDP Sciences, SIF, Springer-Verlag Berlin Heidelberg, 2011