Title :
A sufficient condition for absolute stability of a larger class of dynamical neural networks
Author :
Arik, Sabri ; Tavsanoglu, Vedat
Author_Institution :
Dept. of Electron., Istanbul Univ., Turkey
fDate :
5/1/2000 12:00:00 AM
Abstract :
In this paper, we present a sufficient condition for absolute stability of a larger class of dynamical neural networks. It is shown that the H-matrix condition on the interconnection matrix ensures the existence, uniqueness and global asymptotic stability (GAS) of the equilibrium point with respect to slope-limited activation functions
Keywords :
absolute stability; asymptotic stability; matrix algebra; neural nets; transfer functions; H-matrix condition; absolute stability; dynamical neural networks; equilibrium point; global asymptotic stability; interconnection matrix; slope-limited activation functions; sufficient condition; Asymptotic stability; Circuit stability; Design optimization; Matrix converters; Neural networks; Neurons; Nonlinear dynamical systems; Quadratic programming; Stability analysis; Sufficient conditions;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
