A simple and high performance neural network for quadratic programming problems

被引：28
|
作者：
Tao, Q [1 ]
Cao, JD
Sun, DM
机构：
[1] Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China
[2] Southeast Univ, Dept Appl Math, Nanjing 210096, Peoples R China
来源：
APPLIED MATHEMATICS AND COMPUTATION | 2001年 / 124卷 / 02期
关键词：
neural networks; quadratic programming problems; global convergence; constraint gradient; feasible solution;
D O I：
10.1016/S0096-3003(00)00097-7
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
In this paper, a neural network for quadratic programming problems is simplified. The simplicity is necessary for the high accuracy of solutions and low cost of implementation. The proposed network is proved to be an extension of Newton's optimal descent flow about constraints problems and is globally convergent. The network dynamic behaviors are also discussed and these can get the feasible solution more easily. The simulations demonstrate the reasonability of the theory and advantages of the network. (C) 2001 Elsevier Science Inc. All rights reserved.
引用
收藏
页码：251 / 260
页数：10
相关论文
共 50 条
  • [41] Solving for a quadratic programming with a quadratic constraint based on a neural network frame
    Tan, Y
    Deng, C
    NEUROCOMPUTING, 2000, 30 (1-4) : 117 - 128
  • [42] Convex quadratic programming relaxations for network scheduling problems
    Skutella, M
    ALGORITHMS - ESA'99, 1999, 1643 : 127 - 138
  • [43] A recurrent neural network with finite-time convergence for convex quadratic bilevel programming problems
    Feng, Jiqiang
    Qin, Sitian
    Shi, Fengli
    Zhao, Xiaoyue
    NEURAL COMPUTING & APPLICATIONS, 2018, 30 (11): : 3399 - 3408
  • [44] A novel neural network for solving convex quadratic programming problems subject to equality and inequality constraints
    Huang, Xinjian
    Lou, Yang
    Cui, Baotong
    NEUROCOMPUTING, 2016, 214 : 23 - 31
  • [45] LINEAR AND QUADRATIC-PROGRAMMING NEURAL NETWORK ANALYSIS
    MAA, CY
    SHANBLATT, MA
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (04): : 580 - 594
  • [46] A new delayed projection neural network for solving quadratic programming problems subject to linear constraints
    Niu, Jiuxiao
    Liu, Deyou
    APPLIED MATHEMATICS AND COMPUTATION, 2012, 219 (06) : 3139 - 3146
  • [47] A NOVEL RECURRENT NEURAL NETWORK FOR SOLVING MLCPs AND ITS APPLICATION TO LINEAR AND QUADRATIC PROGRAMMING PROBLEMS
    Effati, Sohrab
    Ghomashi, Abbas
    Abbasi, Masumeh
    ASIA-PACIFIC JOURNAL OF OPERATIONAL RESEARCH, 2011, 28 (04) : 523 - 541
  • [48] A Nonlinear Projection Neural Network for Solving Interval Quadratic Programming Problems and Its Stability Analysis
    Wu, Huaiqin
    Shi, Rui
    Qin, Leijie
    Tao, Feng
    He, Lijun
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2010, 2010
  • [49] A Gradient-Based Neural Network Method for Solving Strictly Convex Quadratic Programming Problems
    Nazemi, Alireza
    Nazemi, Masoomeh
    COGNITIVE COMPUTATION, 2014, 6 (03) : 484 - 495
  • [50] A Gradient-Based Neural Network Method for Solving Strictly Convex Quadratic Programming Problems
    Alireza Nazemi
    Masoomeh Nazemi
    Cognitive Computation, 2014, 6 : 484 - 495
12345