作者: Salete Esteves , José J. Oliveira
DOI: 10.1016/J.AMC.2015.04.103
关键词: Applied mathematics 、 Mathematical proof 、 Exponential stability 、 Artificial neural network 、 Lyapunov functional 、 Mathematical optimization 、 Stability (learning theory) 、 Bidirectional associative memory 、 Mathematics
摘要: For a general Cohen-Grossberg neural network model with potentially unbounded time-varying coefficients and infinite distributed delays, we give sufficient conditions for its global asymptotic stability. The studied is enough to include, as subclass, the most of famous models such Cohen-Grossberg, Hopfield, bidirectional associative memory. Contrary usual in literature, proofs do not use Lyapunov functionals. As illustrated, results are applied several concrete literature comparison shows that our new stability criteria improve some earlier publications.