Title :
A new LMI condition for delay-dependent asymptotic stability of delayed Hopfield neural networks
Author :
Xu, Shengyuan ; Lam, James ; Ho, Daniel W C
Author_Institution :
Dept. of Autom., Nanjing Univ. of Sci. & Technol., China
fDate :
3/1/2006 12:00:00 AM
Abstract :
In this paper, a new delay-dependent asymptotic stability condition for delayed Hopfield neural networks is given in terms of a linear matrix inequality, which is less conservative than existing ones in the literature. This condition guarantees the existence of a unique equilibrium point and its global asymptotic stability of a given delayed Hopfield neural network. Examples are provided to show the reduced conservatism of the proposed condition.
Keywords :
Hopfield neural nets; asymptotic stability; delays; linear matrix inequalities; LMI condition; delay-dependent asymptotic stability; delayed Hopfield neural networks; global asymptotic stability; linear matrix inequality; time delays; Artificial neural networks; Associative memory; Asymptotic stability; Delay effects; Educational programs; Hopfield neural networks; Image reconstruction; Linear matrix inequalities; Stability analysis; Symmetric matrices; Global asymptotic stability; Hopfield neural networks; linear matrix inequality; time delays;
Journal_Title :
Circuits and Systems II: Express Briefs, IEEE Transactions on
DOI :
10.1109/TCSII.2005.857764
