• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2010 International Conference on Multimedia Technology >Immune Genetic Algorithm Optimization and Application
【24h】

Immune Genetic Algorithm Optimization and Application

机译：免疫遗传算法的优化与应用

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper discusses the limitations of the genetic algorithm and the unique advantages of immune genetic algorithm. A clustering based vaccine extraction algorithm is proposed which is being proved to be efficient and reasonable. The clustering based selection method is used to reduce the similarity between antibodies and avoid falling into local optimal solution. In order to speed up the convergence rate, elite antibodies are trained by the steepest descent method. Finally, the new algorithm is applied to the neural networks based Chinese word segmentation model. Experiments show that the accuracy achieved by the new algorithm is much higher than the traditional BP algorithm.
机译：本文讨论了遗传算法的局限性和免疫遗传算法的独特优势。提出了一种基于聚类的疫苗提取算法，该算法被证明是有效且合理的。基于聚类的选择方法用于降低抗体之间的相似性，避免陷入局部最优解。为了加快收敛速度​​，通过最速下降法训练了精英抗体。最后，将该新算法应用于基于神经网络的中文分词模型。实验表明，新算法实现的精度比传统的BP算法高得多。

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