Please use this identifier to cite or link to this item:
Title: Design of exponential state estimators for neural networks with mixed time delays
Authors: Liu, Y
Wang, Z
Liu, X
Keywords: State estimator;Recurrent neural networks;Discrete and distributed delays;Lyapunov–Krasovskii functional;Linear matrix inequality
Issue Date: 2007
Publisher: Elsevier
Citation: Physics Letters A, 364(5): 401-412, May 2007
Abstract: In this Letter, the state estimation problem is dealt with for a class of recurrent neural networks (RNNs) with mixed discrete and distributed delays. The activation functions are assumed to be neither monotonic, nor differentiable, nor bounded. We aim at designing a state estimator to estimate the neuron states, through available output measurements, such that the dynamics of the estimation error is globally exponentially stable in the presence of mixed time delays. By using the Laypunov–Krasovskii functional, a linear matrix inequality (LMI) approach is developed to establish sufficient conditions to guarantee the existence of the state estimators. We show that both the existence conditions and the explicit expression of the desired estimator can be characterized in terms of the solution to an LMI. A simulation example is exploited to show the usefulness of the derived LMI-based stability conditions.
Description: This is the post print version of the article. The official published version can be obtained from the link below - Copyright 2007 Elsevier Ltd.
ISSN: 0375-9601
Appears in Collections:Computer Science
Dept of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
Fulltext.pdf186.99 kBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.