Global asymptotic stability of nonautonomous Cohen-Grossberg neural network models with infinite delays

摘要

For a general Cohen-Grossberg neural network model with potentially unbounded time-varyingcoeffi cients and infi nite distributed delays, we give su fficient conditions for its global asymptoticstability. The model studied is general enough to include, as subclass, the most of famousneural network models such as Cohen-Grossberg, Hopfi eld, and bidirectional associative memory.Contrary to usual in the literature, in the proofs we do not use Lyapunov functionals. Asillustrated, the results are applied to several concrete models studied in the literature and acomparison of results shows that our results give new global stability criteria for several neuralnetwork models and improve some earlier publications.