The stability and design of nonlinear neural networks
暂无分享,去创建一个
Abstract Based on the techniques of singular value decomposition and generalized inverse, two new methods for designing associative memories are presented. The two methods not only guarantee that each given vector is an equilibrium point of the network, but also guarantee the asymptotic stability of the equilibrium points. Examples show the effectiveness of the new methods.
[1] Ömer Morgül,et al. On the design of dynamic associative neural memories , 1994, IEEE Trans. Neural Networks.
[2] Adi Ben-Israel,et al. Generalized inverses: theory and applications , 1974 .
[3] Allon Guez,et al. On the stability, storage capacity, and design of nonlinear continuous neural networks , 1988, IEEE Trans. Syst. Man Cybern..
[4] Anthony N. Michel,et al. A synthesis procedure for Hopfield's continuous-time associative memory , 1990 .