论文信息 - Estimation of the Domain of Attraction and the Convergence Rate of a Hopfield Associative Memory and an Application

Estimation of the Domain of Attraction and the Convergence Rate of a Hopfield Associative Memory and an Application

In this paper, the domain of attraction of memory patterns and the exponential convergence rate of the network trajectories to memory patterns for Hopfield continuous associative memory are estimated. These results can be used for the evaluation of fault-tolerance capability and the synthesis procedures for Hopfield continuous feedback associative memory neural networks, and they are easy to check and apply in practice.

Jinde Cao | Qing Tao | Jinde Cao | Qing Tao

[1] Amir F. Atiya,et al. An analog feedback associative memory , 1993, IEEE Trans. Neural Networks.

[2] A.N. Michel,et al. Associative memories via artificial neural networks , 1990, IEEE Control Systems Magazine.

[3] D. A. Castanon. Qualitative analysis of large scale dynamical systems , 1982 .

[4] Anthony N. Michel,et al. A synthesis procedure for Hopfield's continuous-time associative memory , 1990 .

[5] J J Hopfield,et al. Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[6] Liang Xuebin,et al. Estimation of attraction domain and exponential convergence rate of continuous feedback associative memory and its applications , 1996 .