NEURAL NETWORK WITH STATE-DEPENDENT SYNAPSES

被引：5

作者：

MATUS, IJ

PEREZ, P

机构：

[1] Departamento de Fisica, Universidad de Santiago, Santiago, Casilla 307

来源：

PHYSICAL REVIEW A | 1990年 / 41卷 / 12期

关键词：

D O I：

10.1103/PhysRevA.41.7013

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

A neural network with variable but state-dependent synaptic strengths is discussed. It is shown that the efficiency in retrieving and storing information is enhanced as compared with the Hopfield model and the usual Hebb memorization rule. A nonopinionated learning capacity is discovered. © 1990 The American Physical Society.

引用

页码：7013 / 7019

页数：7

共 17 条

[1] SPIN-GLASS MODELS OF NEURAL NETWORKS [J].

AMIT, DJ ;

GUTFREUND, H .

PHYSICAL REVIEW A, 1985, 32 (02) :1007-1018

[2] NUMBER OF STABLE POINTS FOR SPIN-GLASSES AND NEURAL NETWORKS OF HIGHER ORDERS [J].

BALDI, P ;

VENKATESH, SS .

PHYSICAL REVIEW LETTERS, 1987, 58 (09) :913-916

[3] ASSOCIATIVE MEMORY WITH HIGH INFORMATION-CONTENT [J].

BUHMANN, J ;

DIVKO, R ;

SCHULTEN, K .

PHYSICAL REVIEW A, 1989, 39 (05) :2689-2692

[4] OPTIMAL STORAGE PROPERTIES OF NEURAL NETWORK MODELS [J].

GARDNER, E ;

DERRIDA, B .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1988, 21 (01) :271-284

[5] THE SPACE OF INTERACTIONS IN NEURAL NETWORK MODELS [J].

GARDNER, E .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1988, 21 (01) :257-270

[6]

GUYON I, 1988, NEURAL INFORMATION P, P233

[7]

HEBB DO, 1949, ORG BEHAVIOR

[8] NEURONS WITH GRADED RESPONSE HAVE COLLECTIVE COMPUTATIONAL PROPERTIES LIKE THOSE OF 2-STATE NEURONS [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1984, 81 (10) :3088-3092

[9] 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

[10]

KANDEL ER, 1982, PRINCIPLES NEURAL SC

← 1 2 →