EVOLVING A LEARNING ALGORITHM FOR THE BINARY PERCEPTRON

被引：26

作者：

FONTANARI, JF ^{[1
]}

MEIR, R ^{[1
]}

机构：

[1] BELLCORE,MORRISTOWN,NJ 07960

来源：

NETWORK-COMPUTATION IN NEURAL SYSTEMS | 1991年 / 2卷 / 04期

关键词：

D O I：

10.1088/0954-898X/2/4/002

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We employ a genetic algorithm to explore the space of learning algorithms for a single-layer, binary-weight neural network. We find that the directed drift algorithm, proposed recently by Venkatesh, emerges spontaneously from the genetic tournaments as the local and on-line algorithm that performs best in highly diverse environments.

引用

页码：353 / 359

页数：7

共 17 条

[1]

BELEW RK, 1990, CSE CS90174 U CAL TE

[2]

CHALMERS D, 1990, 1990 P CONN MOD SUMM

[3]

DERRIDA B, 1991, FINITE SIZE EFFECTS

[4]

Duda R. O., 1973, PATTERN CLASSIFICATI, V3

[5] LANDSCAPE STATISTICS OF THE BINARY PERCEPTRON [J].

FONTANARI, JF ;

KOBERLE, R .

JOURNAL DE PHYSIQUE, 1990, 51 (13) :1403-1413

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

GARDNER, E .

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

[7] 3 UNFINISHED WORKS ON THE OPTIMAL STORAGE CAPACITY OF NETWORKS [J].

GARDNER, E ;

DERRIDA, B .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1989, 22 (12) :1983-1994

[8]

Garey M.R., 1979, COMPUTERS INTRACTABI, V174

[9]

Goldberg DE, 1989, GENETIC ALGORITHMS S

[10] 1ST-ORDER TRANSITION TO PERFECT GENERALIZATION IN A NEURAL NETWORK WITH BINARY SYNAPSES [J].

GYORGYI, G .

PHYSICAL REVIEW A, 1990, 41 (12) :7097-7100

← 1 2 →