互联网 qkzz.net
全刊杂志网:首页 > 女性 > 文章正文
刊社推荐

基于面向对象自适应粒子群算法的神经网络训练


□ 徐乐华 凌卫新 熊丽琼

  (1.华南理工大学 数学科学学院, 广州 510640; 2.江西师范大学 计算机信息工程学院, 南昌 330022)
  
  摘 要:针对传统的神经网络训练算法收敛速度慢和泛化性能低的缺陷,提出一种新的基于面向对象的自适应粒子群优化算法(OAPSO)用于神经网络的训练。该算法通过改进PSO的编码方式和自适应搜索策略以提高网络的训练速度与泛化性能,并结合Iris和Ionosphere分类数据集进行测试。实验结果表明:基于OAPSO算法训练的神经网络在分类准确率上明显优于BP算法及标准PSO算法,极大地提高了网络泛化能力和优化效果,具有快速全局收敛的性能。
  关键词:神经网络; 粒子群优化算法; 面向对象方法; 拓扑结构优化
  中图分类号:TP183 文献标志码:A
   文章编号:10013695(2009)01011103
  
  Neural network training based on objectoriented adaptiveparticle swarm optimization
  XU Lehua1, LIN Weixin1, XIONG Liqiong2
  
  (1.School of Mathematics Science, South China University of Technology, Guangzhou 510640, China; 2.School of Computer & Information Engineering, Jiangxi Normal University, Nanchang 330022, China)
  
  Abstract:In view of the traditional neural network training algorithm defects of slow convergence speed and the low generalization, this paper proposed a novel objectoriented adaptive particle swarm optimization(OAPSO) algorithm in the neural network training. This algorithm enhanced the training speed and the generalization ofnetwork through improving the encoding method and the selfadapted search strategy of PSO. Then, used two standard data sets, Iris and Ionosphere, in the test. The experiments show that the neural network based on OAPSO algorithm is obviously superior to BP algorithm and standard PSO algorithm in the classification accuracy rate, and enhances the generalization and the optimized effect of the network. This algorithm has the performance of rapid global convergence. ......
很抱歉,暂无全文,若需要阅读全文或喜欢本刊物请联系《计算机应用研究》杂志社购买。
欢迎作者提供全文,请点击编辑
分享:
 

了解更多资讯,请关注“木兰百花园”
分享:
 
精彩图文


关键字
支持中国杂志产业发展,请购买、订阅纸质杂志,欢迎杂志社提供过刊、样刊及电子版。
关于我们 | 网站声明 | 刊社管理 | 网站地图 | 联系方式 | 中图分类法 | RSS 2.0订阅 | IP查询
全刊杂志赏析网 2017