Global exponential stability for uncertain delayed neural networks of neutral type with mixed time delays

Chang-Hua Lien; Ker-Wei Yu; Yen-Feng Lin; Yeong-Jay Chung; Long-Yeu Chung

doi:10.1109/TSMCB.2008.918564

Global exponential stability for uncertain delayed neural networks of neutral type with mixed time delays

IEEE Trans Syst Man Cybern B Cybern. 2008 Jun;38(3):709-20. doi: 10.1109/TSMCB.2008.918564.

Authors

Chang-Hua Lien¹, Ker-Wei Yu, Yen-Feng Lin, Yeong-Jay Chung, Long-Yeu Chung

Affiliation

¹ Department of Marine Engineering, National Kaohsiung Marine University, Kaohsiung 811, Taiwan, ROC. chlien@mail.nkmu.edu.tw

PMID: 18558536
DOI: 10.1109/TSMCB.2008.918564

Abstract

The global exponential stability for a class of uncertain delayed neural networks (DNNs) of neutral type with mixed delays is investigated in this paper. Delay-dependent and delay-independent stability criteria are proposed to guarantee the robust stability and uniqueness of equilibrium point of DNNs via linear matrix inequality and Razumikhin-like approaches. Two classes of perturbations on weighting matrices are considered in this paper. Some numerical examples are illustrated to show the effectiveness of our results.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Computer Simulation
Models, Statistical*
Neural Networks, Computer*
Signal Processing, Computer-Assisted*
Time Factors*