Solving convex programming problems with equality constraints by neural networks

被引：29

作者：

Chen, YH ^{[1
]}

Fang, SC

机构：

[1] Fruit Loom, Operat Res, Bowling Green, KY 42102 USA

[2] N Carolina State Univ, Raleigh, NC 27695 USA

来源：

COMPUTERS & MATHEMATICS WITH APPLICATIONS | 1998年 / 36卷 / 07期

关键词：

convex programming; penalty function; artificial neural networks; Hopfield networks;

D O I：

10.1016/S0898-1221(98)00172-2

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

This paper presents a neural network approach for solving convex programming problems with equality constraints. After defining the energy function and neural dynamics of the proposed neural network, we show the existence of an equilibrium point at which the neural dynamics becomes asymptotically stable. It is shown that under proper conditions, an optimal solution of the underlying convex programming problems is an equilibrium point of the neural dynamics, and vise verse. The configuration of the proposed neural network with an exact layout is provided for solving linear programming problems. The operational characteristics of the neural network are demonstrated by numerical examples. (C) 1998 Elsevier Science Ltd. All rights reserved.

引用

页码：41 / 68

页数：28

共 35 条

[31] ANALOG NEURAL NETWORK FOR SOLVING THE ASSIGNMENT PROBLEM [J].