DOI: 10.5176/2251-1911_CMCGS16.4
Authors: Cong Jin, Shu-Wei Jin, Junmin Ye1 and Qingguo Zhang
Abstract: The asymptotic behavior of discrete Hopfield neural network is analyzed in this paper. Some properties for discrete Hopfield neural network, such as the trajectory boundary, the uniqueness of equilibrium point and the absolute stability of an equilibrium point, are detail researched. The some sufficient conditions, such as the existence of unique equilibrium point and absolute stability of equilibrium point for discrete Hopfield neural networks are discussed in this paper. Applications of these results only require verifying a matrix or an inequality. These results are also used for the synthesis procedures of discrete Hopfield neural networks.
Keywords: neural networks; absolute stability; asymptotic behavior; equilibrium point
Updating...