Absolute stability criterion for discrete time neural networks

21 December 1994

journal article
Published by IOP Publishing in Journal of Physics A: General Physics

Vol. 27 (24) , L927-L930
https://doi.org/10.1088/0305-4470/27/24/004

Abstract

We give an absolute stability criterion for additive neural networks with discrete time dynamics, i.e. we show that there exists a value for the gain parameter of the sigmoidal transfer function below which the system admits only one fixed point, attracting all trajectories. As an example, we compute this value in the case of random synaptic weights and a fully connected net, in the thermodynamic limit.

Keywords

This publication has 11 references indexed in Scilit:

Mean-field equations, bifurcation map and route to chaos in discrete time neural networks
Physica D: Nonlinear Phenomena, 1994
CONTROL OF THE TRANSITION TO CHAOS IN NEURAL NETWORKS WITH RANDOM CONNECTIVITY
International Journal of Bifurcation and Chaos, 1993
Suppressing chaos in neural networks by noise
Physical Review Letters, 1992
Stability conditions for nonlinear continuous neural networks with asymmetric connection weights
Neural Networks, 1992
Chaos in Highly Diluted Neural Networks
Europhysics Letters, 1991
Stability in contractive nonlinear neural networks
IEEE Transactions on Biomedical Engineering, 1990
Convergent activation dynamics in continuous time networks
Neural Networks, 1989
Chaos in Random Neural Networks
Physical Review Letters, 1988
On the stability, storage capacity, and design of nonlinear continuous neural networks
IEEE Transactions on Systems, Man, and Cybernetics, 1988
Random Matrices in Physics
SIAM Review, 1967