摘要
为了研究Ｈｏｐｆｉｅｌｄ神经网络解决ＴＳＰ（ｔｒａｖｅｌｉｎｇｓａｌｅｓｍａｎｐｒｏｂｌｅｍ）的算法中网络参数和城市拓扑对网络性能的影响，利用计算机模拟Ｈｏｐｆｉｅｌｄ神经网络求解ＴＳＰ的思路、算法．依据大量运算结果对参数和城市拓扑进行了分析，并得出以下结论：（１）Ｈｏｐｆｉｅｌｄ对网络参数的假定值并不是最佳值，参数Ｄ对于网络的性能有比较明显的影响，Ｄ取１００时，网络的收敛率大大提高；而参数Ａ，Ｂ，Ｃ对网络性能的影响并无明显规律，Ａ，Ｂ可以定义在４００～７００的范围内，Ｃ可以在１５０～２５０之间．（２）城市拓扑结构是影响神经网络性能最重要的因素之一．
To study the effection of network parameters and topology of city on Hopfield NN on solving TSP, computer simulation is used and the idea and algorithm of Hopfield NN on solving TSP is carried out.According to the calculating results on parameters and topology of city, the correspondent conclusion have been given.First, the premised values to network parameters made by Hopfield are not the best values.The parameter D has a major influence on the performance on network.When D equals to 100, the convergence ration of network enhanced largely.There are no obvious rules to tell the influence on performance of network made by parameters A, B, C.A and [WTBX]B could be defined between 400 and 700.C could be set among 150 to 250.Second, the topology of a city is one of the most important factors to the influence on network performance, which mean both the convergence ratio and the quality of the path.
出处
《北京邮电大学学报》
EI
CAS
CSCD
北大核心
1999年第2期58-61,共4页
Journal of Beijing University of Posts and Telecommunications
