A new neural network for solving linear and quadratic programming problems

被引：200

作者：

Xia, YS

机构：

[1] Department of Mathematics, Nanjing University of Posts and Telecommunication

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1996年 / 7卷 / 06期

关键词：

D O I：

10.1109/72.548188

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new neural network for solving linear and quadratic programming problems is presented and is shown to be globally convergent. The new neural network improves existing neural networks for solving these problems, that is, it avoids the parameter turning problem, is capable of achieving the exact solutions, and uses only simple hardware in which no analog multipliers for variables are required. Furthermore, the network salves both the primal problems and their dual problems simultaneously.

引用

页码：1544 / 1547

页数：4

共 12 条

[1]

[Anonymous], IEEE T NEURAL NETWOR

[2]

BOUZERDOUM A, 1993, IEEE T NEURAL NETWOR, V4

[3]

HOPFIELD JJ, 1986, IEEE T CIRCUITS SYST, V33

[4]

HOPFIELD JJ, 1985, BIOL CYBERN, V52

[5]

KENNEDY MP, 1988, IEEE T CIRCUITS SYST, V35

[6]

LUENBERGER DG, 1937, INTRO LINEAR NONLINE

[7]

Miller RK, 1982, ORDINARY DIFFERENTIA

[8]

RODRIGUEZVAZQUE.A, 1990, IEEE T CIRCUITS SYST, V37

[9] A high-performance neural network for solving linear and quadratic programming problems [J].

Wu, XY ;

Xia, YS ;

Li, JM ;

Chen, WK .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (03) :643-651

[10]

XIA Y, UNPUB IEEE T NEURAL

← 1 2 →