Title :
Stability of asymmetric Hopfield networks
Author :
Chen, Tianping ; Amari, Shun Ichi
Author_Institution :
Inst. of Math., Fudan Univ., Shanghai, China
fDate :
1/1/2001 12:00:00 AM
Abstract :
In this paper, we discuss dynamical behaviors of recurrently asymmetrically connected neural networks in detail. We propose an effective approach to study global and local stability of the networks. Many of well known existing results are unified in our framework, which gives much better test conditions for global and local stability. Sufficient conditions for the uniqueness of the equilibrium point and its stability conditions are given, too
Keywords :
Hopfield neural nets; recurrent neural nets; stability criteria; asymmetric Hopfield networks; dynamical behaviors; equilibrium point; global stability; local stability; recurrently asymmetrically connected neural networks; stability conditions; stability criteria; Chaos; Differential equations; Hopfield neural networks; Lyapunov method; Mathematics; Neural networks; Recurrent neural networks; Stability; Sufficient conditions; Testing;
Journal_Title :
Neural Networks, IEEE Transactions on
