A NEW NEURAL NETWORK APPROACH OF LINEAR PROGRAMMING

摘要：

This paper presents a new neural network for solving linear programming problems. After defining the neural dynamics of the proposed neural network, we have shown the existence of an equilibrium point and the asymptotic stability of the equilibrium point of the neural dynamics. As the time parameter approaches infinity, an optimal solution of the linear programming problem is shown to be the equilibrium point of the neural dynamics, and each equilibrium point is optimal to the problem. Two numerical results indicate that the proposed neural network is an efficient technique and stable independent of the starting point.

关键词： Neural network Linear programming Differential equation Asymptotically stable

作者: WEI LI

作者单位: School of Science, Hangzhou Dianzi University, Hangzhou 310018

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 723-727

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）