基于神经网络的最短路算法及其应用  

Neural Network for Shortest Path Algorithm and Its Application

作　　者：马传水[1] 阮传概[1] 

机构地区：[1]北京邮电大学信息工程系,北京100876

出　　处：《北京邮电大学学报》1999年第4期9-13,共5页Journal of Beijing University of Posts and Telecommunications

摘　　要：提出了一种基于递归神经网络（ｒｅｃｕｒｒｅｎｔ ｎｅｕｒａｌｎｅｔｗ ｏｒｋ）的最短路算法， 降低了神经元之间的连接复杂度， 能稳定收敛到准最优解， 并将其应用于基于流量的动态分布式路由．仿真表明，A shortest path algorithm based on recurrent neural network (RSP) is proposed, which decreases complexity of connections among units, compared with Hopfield neural network. Simulations show that the algorithm converges to near optimal solutions steadily. While it can be applied to dynamic distributed routing algorithm based on flow.

关 键 词：神经网络 最短路算法 组合优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]