J4

• 数学 • 上一篇    下一篇

神经网络在二次规划问题中的应用

王 勇1, 伍铁如2, 马儒宁3   

  1. 1. 长春工业大学 基础科学学院, 长春 130012; 2 吉林大学 数学研究所, 长春 130012;3. 南京航空航天大学 数学系, 南京 210016
  • 收稿日期:2007-11-02 修回日期:1900-01-01 出版日期:2008-05-26 发布日期:2008-05-26
  • 通讯作者: 王 勇

Neural Network for Solving Quadratic Programming Problems

WANG Yong1, WU Tieru2, MA Runing3   

  1. 1. College of Basic Sciences, Changchun University of Technology, Changchun 130012, China;2. Institute of Mathematics, Jilin University, Changchun 130012, China;3. Department of Mathematics, Nanjing University of Aeronautics & Astronautics, Nanjing 210016, China
  • Received:2007-11-02 Revised:1900-01-01 Online:2008-05-26 Published:2008-05-26
  • Contact: WANG Yong

摘要: 利用对偶神经网络解决了基于线性等式、 不等式和有 界约束的二次规划问题, 表明所研究的对偶神经网络具有整体指数收敛性, 与包含高次非线性条件的神经网络相比, 所提出的网络使用了更少的神经元, 并且网络的体系结构更简单.数值实验结果表明了该方法的有效性.

关键词: 神经网络, 二次规划问题, 指数收敛

Abstract: This paper presents a dual neural network which is globally exponential convergence for solving quadratic programming problems based on linear equation, inequation and bounded constraint. Compared with other neural network models which contained highorder nonlinear condition, the dual neural network uses less neuron and has simpler structure. Finally, numerical tests show the validity of the model.

Key words: neural network, quadratic programming problems, expon ential convergence

中图分类号: 

  • O24