首页> 外文会议>Proceedings of the 2007 International Conference on Machine Learning and Cybernetics >AN EFFICIENT SHORTEST PATH ROUTING ALGORITHM BASED ON IMPROVED CHAOTIC NEURAL NETWORK
【24h】

AN EFFICIENT SHORTEST PATH ROUTING ALGORITHM BASED ON IMPROVED CHAOTIC NEURAL NETWORK

机译:基于改进混沌神经网络的最短路径路由算法

获取原文

摘要

In this paper an efficient shortest path algorithm, which is an improved version of the transient chaotic neural network (TCNN), is presented.By eliminating the components of the eigenvectors with eminent negative eigenvalues of the weight matrix, this proposed method can avoid oscillation and offer a considerable acceleration of converging to the optimal solution when TCNN is used to search the optimal solution of shortest path problems.Numerical simulations of shortest path problem show that TCNN with modified weight matrix requires less iteration than TCNN with standard weight matrix before reaching optimal solution.
机译:本文提出了一种有效的最短路径算法,它是瞬态混沌神经网络(TCNN)的改进版本。当使用TCNN搜索最短路径问题的最优解时,可以大大加快收敛到最优解的速度。最短路径问题的数值模拟表明,具有改进权重矩阵的TCNN与具有标准权重矩阵的TCNN相比,迭代次数更少。 。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号