Title :
New Lyapunov methodology: asymptotic stability of Hopfield neural networks
Author :
Grujic, Ljuborrmir
Author_Institution :
Ecole Nat. de Ingenieurs, Belfort, France
Abstract :
The paper develops a new Lyapunov methodology for Hopfield neural networks (HNN). It determines an algorithm for an exact construction of a Lyapunov function v(.) for given HNN, which is based on a complete set of the necessary and sufficient conditions for (global) asymptotic stability of the isolated equilibrium state x=0
Keywords :
Hopfield neural nets; Lyapunov methods; asymptotic stability; nonlinear systems; Hopfield neural networks; Lyapunov function; Lyapunov methodology; algorithm; asymptotic stability; global stability; isolated equilibrium state; Asymptotic stability; Equations; Hopfield neural networks; Inductors; Linear systems; Lyapunov method; Neural networks; Nonlinear systems; Sufficient conditions; System testing;
Conference_Titel :
Industrial Electronics, 1996. ISIE '96., Proceedings of the IEEE International Symposium on
Conference_Location :
Warsaw
Print_ISBN :
0-7803-3334-9
DOI :
10.1109/ISIE.1996.548404
