Title :
Stability Criteria With Less LMI Variables for Neural Networks With Time-Varying Delay
Author :
Li, Tao ; Guo, Lei ; Lin, Chong
Author_Institution :
Res. Inst. of Autom., Southeast Univ., Nanjing
Abstract :
In this letter, simplified delay-dependent stability criteria for neural networks are derived by using a simple integral inequality. The results are in terms of linear matrix inequalities (LMIs) and turn out to be equivalent to some existing results but include less number of LMI variables. This implies that some redundant variables in the existing stability criteria can be removed while maintaining the efficiency of the stability conditions. With the present stability conditions, the computational burden is largely reduced. Numerical examples are given to verify the effectiveness of the proposed criteria.
Keywords :
linear matrix inequalities; neural nets; stability criteria; time-varying systems; delay dependent stability criteria; integral inequality; linear matrix inequalities; neural networks; stability conditions; time-varying delay; Artificial neural networks; Automation; Delay effects; Linear matrix inequalities; Maintenance engineering; Neural networks; Neurons; Pattern recognition; Stability criteria; Symmetric matrices; Asymptotic stability; delay-dependent; neural networks (NNs);
Journal_Title :
Circuits and Systems II: Express Briefs, IEEE Transactions on
DOI :
10.1109/TCSII.2008.2004539