Title :
Absolute stability of nonsymmetric neural networks
Author :
Arik, Sabri ; Tavsanoglu, Vedat
Author_Institution :
Centre for Res. in Inf. Eng., South Bank Univ., London, UK
Abstract :
In this paper, two conditions concerning absolute stability of nonsymmetric dynamical neural networks are presented. Each condition guarantees the uniqueness and global asymptotic stability of the equilibrium point for different classes of activation functions and under different constraint conditions imposed on the interconnection matrix
Keywords :
absolute stability; asymptotic stability; neural nets; absolute stability; activation functions; constraint conditions; equilibrium point; global asymptotic stability; interconnection matrix; nonsymmetric dynamical neural networks; uniqueness; Asymptotic stability; Equations; Lyapunov method; Neural networks; Sufficient conditions;
Conference_Titel :
Circuits and Systems, 1996. ISCAS '96., Connecting the World., 1996 IEEE International Symposium on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3073-0
DOI :
10.1109/ISCAS.1996.541628
