神经网络方法求解线性规划问题研究

Research on Solving Linear Programming with Neural Networks

线性规划的求解是约束最优化问题的重要研究内容，常采用迭代算法（如单纯形方法），计算量大，耗时昂贵．利用神经网络的本质并行性和高度非线性映射逼近能力，提出了一类求解线性规划问题的前馈神经网络方法，网络构建简单，求解精度高，计算量小．

The problem of solving linear programming is the most important context in the discipline of constrained optimization. Traditional methods for solving linear programming typically involve an iterative process,such as the simplex method,but long computational time limits their usage.In this paper a method of using back error propagation of neural networks is proposed to solve linear programming.This method has little computation,higher result precision and is simple to construct networks.The simulation results prove the method is efficient.