A DILUTION ALGORITHM FOR NEURAL NETWORKS

被引：12

作者：

KUHLMANN, P

GARCES, R

EISSFELLER, H

机构：

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

来源：

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL | 1992年 / 25卷 / 09期

关键词：

D O I：

10.1088/0305-4470/25/9/014

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

A dilution algorithm to enlarge the storage capacity per synapse alpha(eff) of neural networks is proposed. The algorithm is a hybrid method, where Hebb's rule is used to select a fraction of couplings to be removed. Afterwards the perceptron of optimal stability for the remaining couplings is learned. We present an analytical calculation and the results of the numerical simulations. In comparison with the fully connected or the randomly diluted perceptron, the effective storage capacity alpha(eff) is remarkably enlarged.

引用

页码：L593 / L598

页数：6

共 18 条

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

ANLAUF, JK ;

BIEHL, M .

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

[2]

[Anonymous], 1991, INTRO THEORY NEURAL, DOI DOI 10.1201/9780429499661

[3]

BOLLE D, 1991, LEUVEN PREPRINT

[4] QUENCHED VERSUS ANNEALED DILUTION IN NEURAL NETWORKS [J].

BOUTEN, M ;

ENGEL, A ;

KOMODA, A ;

SERNEELS, R .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1990, 23 (20) :4643-4657

[5]

BOUTEN M, COMMUNICATION

[6] GEOMETRICAL AND STATISTICAL PROPERTIES OF SYSTEMS OF LINEAR INEQUALITIES WITH APPLICATIONS IN PATTERN RECOGNITION [J].

COVER, TM .

IEEE TRANSACTIONS ON ELECTRONIC COMPUTERS, 1965, EC14 (03) :326-&

[7] LAYERED NEURAL NETWORKS [J].

DOMANY, E ;

KINZEL, W ;

MEIR, R .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1989, 22 (12) :2081-2102

[8]

GARCES R, 1991, THESIS GIESSEN

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

GARDNER, E ;

DERRIDA, B .

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

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

GARDNER, E .

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

← 1 2 →