ON THE ABILITY OF THE OPTIMAL PERCEPTRON TO GENERALIZE

被引：82

作者：

OPPER, M

KINZEL, W

KLEINZ, J

NEHL, R

机构：

[1] Institut fur Theor. Phys., Justus-Liebig Univ., Giessen

来源：

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL | 1990年 / 23卷 / 11期

关键词：

D O I：

10.1088/0305-4470/23/11/012

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

A linearly separable Boolean function is derived from a set of examples by a perceptron with optimal stability. The probability to reconstruct a pattern which is not learnt is calculated analytically using the replica method.

引用

页码：L581 / L586

页数：6

共 12 条

[1]

Amit D. J., 1989, MODELLING BRAIN FUNC

[2] THE ADATRON - AN ADAPTIVE PERCEPTRON ALGORITHM [J].

ANLAUF, JK ;

BIEHL, M .

EUROPHYSICS LETTERS, 1989, 10 (07) :687-692

[3] LEARNING OF CORRELATED PATTERNS IN SPIN-GLASS NETWORKS BY LOCAL LEARNING RULES [J].

DIEDERICH, S ;

OPPER, M .

PHYSICAL REVIEW LETTERS, 1987, 58 (09) :949-952

[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]

GYORGYI G, 1989, P STATPHYS, V17

[7]

KINZEL W, 1989, IN PRESS PHYSICS NEU

[8]

Kohonen T., 1988, SELF ORG ASS MEMORY

[9] LEARNING ALGORITHMS WITH OPTIMAL STABILITY IN NEURAL NETWORKS [J].

KRAUTH, W ;

MEZARD, M .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1987, 20 (11) :L745-L752

[10] LEARNING TIMES OF NEURAL NETWORKS - EXACT SOLUTION FOR A PERCEPTRON ALGORITHM [J].

OPPER, M .

PHYSICAL REVIEW A, 1988, 38 (07) :3824-3826

← 1 2 →