This paper deals with the problem of state estimation for discrete-time recurrent neural networks with interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. A delay-range-dependent condition for the existence of state estimators is proposed. Via available output measurements and solutions to certain linear matrix inequalities, general full-order state estimators are designed that ensure globally asymptotic stability. Two illustrative examples are given to demonstrate the effectiveness and applicability.
|Number of pages||5|
|Journal||IEEE Transactions on Circuits and Systems II: Express Briefs|
|Publication status||Published - 2008 Dec 30|
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering