Premium
Global exponential stability for uncertain bidirectional associative memory neural networks with multiple time‐varying delays via LMI approach
Author(s) -
Gau RueyShyan,
Hsieh JerGuang,
Lien ChangHua
Publication year - 2008
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/cta.449
Subject(s) - bidirectional associative memory , exponential stability , linear matrix inequality , control theory (sociology) , artificial neural network , content addressable memory , stability (learning theory) , computer science , exponential function , mathematics , mathematical optimization , nonlinear system , artificial intelligence , control (management) , machine learning , mathematical analysis , physics , quantum mechanics
The global exponential stability for uncertain delayed bidirectional associative memory neural networks (DBAMNN) with multiple time‐varying delays is considered in this paper. Delay‐dependent criteria are proposed to guarantee the robust stability of DBAMNN via linear matrix inequality approach. Two classes of system uncertainties are investigated in this paper. Some numerical examples are given to illustrate the effectiveness of our results. From the numerical simulations, significant improvement over the recent results can be observed. Copyright © 2007 John Wiley & Sons, Ltd.