SOLVING LINEAR-PROGRAMMING PROBLEMS WITH NEURAL NETWORKS - A COMPARATIVE-STUDY

被引：84

作者：

ZAK, SH ^{[1
]}

UPATISING, V ^{[1
]}

HUI, S ^{[1
]}

机构：

[1] SAN DIEGO STATE UNIV,DEPT MATH SCI,SAN DIEGO,CA 92182

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1995年 / 6卷 / 01期

关键词：

D O I：

10.1109/72.363446

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we study three different classes of neural network models for solving linear programming problems. We investigate the following characteristics of each model: model complexity, complexity of individual neurons, and accuracy of solution. Simulation examples are given to illustrate the dynamical behavior of each model.

引用

页码：94 / 104

页数：11

共 36 条

[1]

[Anonymous], 2003, LINEAR PROGRAMMING

[2]

[Anonymous], 1988, UNDERGRADUATE TEXTS

[3]

BARTLE RG, 1976, ELEMENTS REAL ANAL, P406

[4] NECESSARY AND SUFFICIENT CONDITIONS FOR A PENALTY METHOD TO BE EXACT [J].