Global exponential stability of recurrent neural networks for solving optimization and related problems

被引：61

作者：

Xia, YS ^{[1
]}

Wang, J ^{[1
]}

机构：

[1] Chinese Univ Hong Kong, Dept Automat & Comp Aided Engn, Hong Kong, Hong Kong, Peoples R China

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2000年 / 11卷 / 04期

关键词：

global exponential stability; optimization problems; recurrent neural networks;

D O I：

10.1109/72.857782

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Global exponential stability is a desirable property for dynamic systems. This paper studies the global exponential stability of several existing recurrent neural networks for solving linear programming problems, convex programming problems with interval constraints, convex programming problems with nonlinear constraints, and monotone variational inequalities. In contrast to the existing results on global exponential stability, the present results do not require additional conditions on the weight matrices of recurrent neural networks and improve some existing conditions for global exponential stability. Therefore, the stability results in this paper further demonstrate the superior convergence properties of the existing neural networks for optimization.

引用

页码：1017 / 1022

页数：6

共 17 条

[1]

Bertsekas Dimitri P., 1989, PARALLEL DISTRIBUTED

[2] NEURAL NETWORK FOR QUADRATIC OPTIMIZATION WITH BOUND CONSTRAINTS [J].

BOUZERDOUM, A ;

PATTISON, TR .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (02) :293-304

[3]

Cichocki A., 1993, Neural Networks for Optimization and Signal Processing

[4] NEURAL NETWORKS FOR NONLINEAR-PROGRAMMING [J].

KENNEDY, MP ;

CHUA, LO .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (05) :554-562

[5] LINEAR AND QUADRATIC-PROGRAMMING NEURAL NETWORK ANALYSIS [J].

MAA, CY ;

SHANBLATT, MA .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (04) :580-594

[6] QUALITATIVE-ANALYSIS OF NEURAL NETWORKS [J].

MICHEL, AN ;

FARRELL, JA ;

POROD, W .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1989, 36 (02) :229-243

[7]

Miller R. K., 1982, Ordinary Differential Equations

[8]

Ortega JM., 1970, ITERATIVE SOLUTION N

[9] A POSTERIORI ERROR-BOUNDS FOR THE LINEARLY-CONSTRAINED VARIATIONAL INEQUALITY PROBLEM [J].

PANG, JS .

MATHEMATICS OF OPERATIONS RESEARCH, 1987, 12 (03) :474-484

[10] Convergence analysis of a discrete-time recurrent neural network to perform quadratic real optimization with bound constraints [J].

Perez-Ilzarbe, MJ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (06) :1344-1351

← 1 2 →