A Delayed Projection Neural Network for Solving Linear Variational Inequalities

被引：52
作者：
Cheng, Long [1 ,2 ]
Hou, Zeng-Guang [1 ]
Tan, Min [1 ]
机构：
[1] Chinese Acad Sci, Key Lab Complex Syst & Intelligence Sci, Inst Automat, Beijing 100190, Peoples R China
[2] Chinese Acad Sci, Grad Univ, Beijing 100049, Peoples R China
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2009年 / 20卷 / 06期
基金：
中国国家自然科学基金;
关键词：
Constrained quadratic programming; linear variational inequality; projection neural network; time delay; GLOBAL ASYMPTOTIC STABILITY; QUADRATIC-PROGRAMMING PROBLEMS; EXPONENTIAL STABILITY; OPTIMIZATION PROBLEMS; DYNAMICAL-SYSTEMS; CONVERGENCE;
D O I：
10.1109/TNN.2009.2012517
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, a delayed projection neural network is proposed for solving a class of linear variational inequality problems. The theoretical analysis shows that the proposed neural network is globally exponentially stable under different conditions. By the proposed linear matrix inequality (LMI) method, the monotonicity assumption on the linear variational inequality is no longer necessary. By employing Lagrange multipliers, the proposed method can resolve the constrained quadratic programming problems. Finally, simulation examples are given to demonstrate the satisfactory performance of the proposed neural network.
引用
收藏
页码：915 / 925
页数：11
相关论文
共 29 条
[11]   Solving generally constrained generalized linear variational inequalities using the general projection neural networks [J].
Hu, Xiaolin ;
Wang, Jun .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (06) :1697-1708
[12]   A recurrent neural network for solving a class of general variational inequalities [J].
Hu, Xiaolin ;
Wang, Jun .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2007, 37 (03) :528-539
[13]   A new constrained independent component analysis method [J].
Huang, De-Shuang ;
Mi, Jian-Xun .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (05) :1532-1535
[14]  
Kinderlehrer D., 1980, An Introduction to Variational Inequalities and Their Applications
[15]   Blind image deconvolution through support vector regression [J].
Li, Dalong ;
Mersereau, Russell M. ;
Simske, Steven .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (03) :931-935
[16]   Global exponential stability of neural networks with globally Lipschitz continuous activations and its application to linear variational inequality problem [J].
Liang, XB ;
Si, J .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (02) :349-359
[17]   LMI-Based approach for asymptotically stability analysis of delayed neural networks [J].
Liao, XF ;
Chen, GR ;
Sanchez, EN .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2002, 49 (07) :1033-1039
[18]   Growth-promoting effects of a bacterium on raphidophytes and other phytoplankton [J].
Liu, Jiqing ;
Lewitus, Alan J. ;
Brown, Patrick ;
Wilde, Susan B. .
HARMFUL ALGAE, 2008, 7 (01) :1-10
[19]   A delayed neural network for solving linear projection equations and its analysis [J].
Liu, QS ;
Cao, JD ;
Xia, YS .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (04) :834-843
[20]   Global exponential stability of bidirectional associative memory neural networks with time delays [J].
Liu, Xin-Ge ;
Martin, Ralph R. ;
Wu, Min ;
Tang, Mei-Lan .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (03) :397-407
123