针对 Hopfield神经网络 ( HNN)学习算法难以求解大规模组合优化问题的不足 ,提出了基于HNN学习的多城市旅行商问题的求解算法 .它是把 HNN学习算法作基本算子 ,对城市群体按一定的规则进行有效的分割、计算和连接 ,来寻找巡回路径的最优解或满意解 .并以 1 0 0城市的旅行商问题为例进行了仿真实验 ,验证了算法的有效性 .该算法不受求解问题的规模限制 ;还可通过并列运算实现高速化 ;同时因算法简明 ,易于硬件实现 . Aiming at the shortage of Hopfield neural network (HNN) learning algorithm to solve large-scale combinatorial optimization problems, this paper proposes a HNN learning algorithm for solving multi-city traveling salesman problem. It takes HNN learning algorithm as the basic operator, To find the optimal solution or satisfactory solution of the touring path through the effective partition, calculation and connection.A simulation experiment is carried out on the traveling salesman problem of 100 cities, which verifies the effectiveness of the algorithm Subject to the size of the problem to be solved; but also through the parallel operation to achieve high-speed; at the same time due to the algorithm is concise, easy to implement the hardware.