The stability of a class of generalized fuzzy Hopfield networks

Abstract

A general dynamical fuzzy neural networks model—fuzzy Hopfield networks is developed, which is based on the fuzzy operator composition of max(V) and weakly continuous T-norms. It is shown that the model is global stable with the Hamming distance, and its equilibrium point (attractor) is Lyapunov stable. At last, a simple efficient learning algorithm —max-weight-matrix learning algorithm is proposed for it.