Stability Criterion of Discrete Hopfield Neural Networks with Weighted Function Matrix and one-Delay
In this paper, discrete Hopfield neural networks with weight function matrix(WFM) and delay(DHNNWFMD) are presented. And we obtain an important result that if the WFM is a symmetric function matrix(SFM) and delayed function matrix(DFM) is a diagonally dominant function matrix(DDFM), DHNNWFMD will converge to a state in serial mode and if the WFM is a SFM and non-negative definite function matrix(NFM) and DFM is a DDFM, DHNNWFMD will converge to a state in parallel mode. It provides some theory basis for the application of DHNNWFMD.
H. Y. Zou et al., "Stability Criterion of Discrete Hopfield Neural Networks with Weighted Function Matrix and one-Delay", Advanced Materials Research, Vols. 271-273, pp. 725-729, 2011