Neurocomputing with time delay analysis for solving convex quadratic programming problems

被引:91
作者
Chen, YH [1 ]
Fang, SC
机构
[1] I2 Technol, Irving, TX 75039 USA
[2] N Carolina State Univ, Raleigh, NC 27695 USA
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2000年 / 11卷 / 01期
关键词
artificial neural network; convex programming; Hopfield network; linear and quadratic programming; time-delay dynamic system;
D O I
10.1109/72.822526
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a neural-network computational scheme with time-delay consideration for solving convex quadratic programming problems, Based on some known results, a delay margin is explicitly determined for the stability of the neural dynamics, under which the states of the neural network does not oscillate. The configuration of the proposed neural network is provided. Operational characteristics of the neural network are demonstrated via numerical examples.
引用
收藏
页码:230 / 240
页数:11
相关论文
共 40 条
[1]   HOW DELAYS AFFECT NEURAL DYNAMICS AND LEARNING [J].
BALDI, P ;
ATIYA, AF .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (04) :612-621
[2]  
Bellman R., 1963, DIFFERENTIAL DIFFERE
[3]   Solving convex programming problems with equality constraints by neural networks [J].
Chen, YH ;
Fang, SC .
COMPUTERS & MATHEMATICS WITH APPLICATIONS, 1998, 36 (07) :41-68
[4]  
CHEN YH, 1997, THESIS N CAROLINA ST
[5]   A new neural network for solving linear programming problems [J].
Cichocki, A ;
Unbehauen, R ;
Weinzierl, K ;
Holzel, R .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 1996, 93 (02) :244-256
[6]   DISCRETE DELAY, DISTRIBUTED DELAY AND STABILITY SWITCHES [J].
COOKE, KL ;
GROSSMAN, Z .
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1982, 86 (02) :592-627
[7]  
Coughlin J.P., 1995, Neural Computation in Hopfield Networks and Boltzmann Machines, Machine Learning Books
[8]  
DATKO R, 1969, P 28 C DEC CONTR TAM, P2032
[9]  
Dennis J. B., 1959, MATH PROGRAMMING ELE
[10]  
Fang S.-C., 1993, Linear Optimization and Extensions: Theory and Algorithms, VFirst