Premium
Global stability analysis of bidirectional associative memory neural networks with time delay
Author(s) -
Zhang Jiye,
Yang Yiren
Publication year - 2001
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/cta.144
Subject(s) - monotonic function , bidirectional associative memory , uniqueness , differentiable function , artificial neural network , content addressable memory , stability (learning theory) , computer science , equilibrium point , control theory (sociology) , activation function , associative property , interconnection , mathematics , topology (electrical circuits) , control (management) , pure mathematics , mathematical analysis , differential equation , artificial intelligence , combinatorics , telecommunications , machine learning
In this paper, without assuming the boundedness, monotonicity and differentiability of the activation functions, we present new conditions ensuring existence, uniqueness, and global asymptotical stability of the equilibrium point of bidirectional associative memory neural networks with fixed time delays or distributed time delays. The results are applicable to both symmetric and non‐symmetric interconnection matrices, and all continuous non‐monotonic neuron activation functions. Copyright © 2001 John Wiley & Sons, Ltd.