STOCHASTIC OPTIMIZATION ALGORITHMS - AN APPLICATION TO PATTERN-MATCHING

被引：6

作者：

BENGTSSON, M

机构：

[1] National Defence Research Establishment of Sweden

来源：

PATTERN RECOGNITION LETTERS | 1990年 / 11卷 / 11期

关键词：

computer vision; digital image matching; Langevin; Stochastic processes;

D O I：

10.1016/0167-8655(90)90090-O

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We have investigated the Langevin stochastic equation of motion with application to a certain optimization problem - pattern matching. This method is similar to simulated annealing techniques with the exception that here the equations of motion governs the path in the parameter space. © 1990.

引用

页码：717 / 724

页数：8

共 7 条

[1]

FEYNMAN RP, 1963, QUANTUM MECHANICS PA

[2]

HOPFIELD JJ, 1985, BIOL CYBERN, V52, P141

[3] 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

[4] OPTIMIZATION BY SIMULATED ANNEALING [J].

KIRKPATRICK, S ;

GELATT, CD ;

VECCHI, MP .

SCIENCE, 1983, 220 (4598) :671-680

[5]

McClelland J. L., 1986, PARALLEL DISTRIBUTED, V1

[6]

PARISI G, 1981, SCI SINICA, V24, P483

[7]

REIF F, 1965, FUNDAMENTALS STATIST

← 1 →