A FINITE-SIZE SCALING INVESTIGATION FOR Q-STATE HOPFIELD MODELS - STORAGE CAPACITY AND BASINS OF ATTRACTION

被引：4

作者：

STIEFVATER, T

MULLER, KR

机构：

[1] Inst. fur Logik, Komplexitat und Deduktions-syst., Karlsruhe Univ.

来源：

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL | 1992年 / 25卷 / 22期

关键词：

D O I：

10.1088/0305-4470/25/22/019

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

The storage capacity of a Q-state Hopfield network is determined via finite-size scaling for parallel dynamics and Q less-than-or-equal-to 8. The results are in good agreement with theoretical predictions by Rieger. The basins of attraction and other associative memory properties are discussed for Q = 4. 6. A self-controlling Q-state model with improved basins of attraction is proposed.

引用

页码：5919 / 5929

页数：11

共 14 条

[1]

GERL S, 1992, LEARNING Q STATE CLO

[2] 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

[3]

HOPFIELD JJ, 1984, P NAT ACAD SCI US, V81

[4] FINITE-STATE NEURAL NETWORKS - A STEP TOWARD THE SIMULATION OF VERY LARGE SYSTEMS [J].

KOHRING, GA .

JOURNAL OF STATISTICAL PHYSICS, 1991, 62 (3-4) :563-576

[5] STATISTICAL-MECHANICS FOR NETWORKS OF GRADED-RESPONSE NEURONS [J].

KUHN, R ;

BOS, S ;

VANHEMMEN, JL .

PHYSICAL REVIEW A, 1991, 43 (04) :2084-2087

[6]

KUHN R, UNPUB

[7]

KUHN R, 1990, SPRINGER LECT NOTES, V368, P19

[8]

LITTLE W A, 1974, Mathematical Biosciences, V19, P101, DOI 10.1016/0025-5564(74)90031-5

[9]

MERTENS S, 1991, LEARNING GREY TONED

[10]

MULLER, 1992, P INT C ARTIFICIAL N

← 1 2 →