WORST-CASE CONVERGENCE TIMES FOR HOPFIELD MEMORIES

被引：10

作者：

FLOREEN, P

机构：

[1] Department of Computer Science, University of Helsinki, Teollisuuskatu 23

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 05期

关键词：

D O I：

10.1109/72.134291

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The worst-case upper bound on the convergence time of Hopfield associative memories is improved to half of its previously known value. Also the consequences of allowing "don't know" bits in both the input and the output are considered.

引用

页码：533 / 535

页数：3

共 4 条

[1] INTERNAL REPRESENTATIONS FOR ASSOCIATIVE MEMORY [J].

BAUM, EB ;

MOODY, J ;

WILCZEK, F .

BIOLOGICAL CYBERNETICS, 1988, 59 (4-5) :217-228

[2] TRANSIENT LENGTH IN SEQUENTIAL ITERATION OF THRESHOLD FUNCTIONS [J].

FOGELMAN, F ;

GOLES, E ;

WEISBUCH, G .

DISCRETE APPLIED MATHEMATICS, 1983, 6 (01) :95-98

[3] DECREASING ENERGY FUNCTIONS AS A TOOL FOR STUDYING THRESHOLD NETWORKS [J].

GOLESCHACC, E ;

FOGELMANSOULIE, F ;

PELLEGRIN, D .

DISCRETE APPLIED MATHEMATICS, 1985, 12 (03) :261-277

[4] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558

← 1 →