本文提出一种求解最大独立集问题(MIS)的启发式神经网络算法。该算法基于MIS问题的特点,有效地限制神经网络初始点的选择范围,并利用神经网络快速收敛能力获得问题的解。与标准神经网络算法相比,该算法显示了较高的全局优化性态与计算效率。模拟计算实例表明了该算法的有效性。 This paper presents a heuristic neural network algorithm for solving the maximal independent set problem (MIS). Based on the characteristics of MIS, the algorithm effectively limits the selection range of the initial point of the neural network and uses the rapid convergence ability of the neural network to obtain the solution of the problem. Compared with the standard neural network algorithm, this algorithm shows a higher global optimization state and computational efficiency. The simulation example shows the effectiveness of the algorithm.