DYNAMICS OF DISCRETE-TIME, CONTINUOUS STATE HOPFIELD NETWORKS

被引：31

作者：

KOIRAN, P

机构：

来源：

NEURAL COMPUTATION | 1994年 / 6卷 / 03期

关键词：

D O I：

10.1162/neco.1994.6.3.459

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The dynamics of discrete time, continuous state Hopfield networks is driven by an energy function. In this paper, we use this tool-to prove under mild hypotheses that any trajectory converges to a fixed point for the sequential iteration, and to a cycle of length 2 or a fixed point for the parallel iteration. Perhaps surprisingly, it seems that no rigorous proof of these results was published before.

引用

页码：459 / 468

页数：10

共 8 条

[1]

FOGELMANSOULIE F, 1989, COMPLEX SYSTEMS, V3, P269

[2]

Goles E., 1990, NEURAL AUTOMATA NETW, DOI 10.1007/978-94-009-0529-0

[3]

Hirsch M. W., 1976, DIFFERENTIAL TOPOLOG, V33

[4] CONVERGENT ACTIVATION DYNAMICS IN CONTINUOUS-TIME NETWORKS [J].