计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (34): 43-45.DOI: 10.3778/j.issn.1002-8331.2010.34.013

• 研究、探讨 • 上一篇    下一篇

神经网络稳定性的交叉验证模型

邱龙金1,贺昌政2   

  1. 1.四川大学 计算机学院,成都 610065
    2.四川大学 工商管理学院,成都 610065
  • 收稿日期:2010-03-12 修回日期:2010-06-17 出版日期:2010-12-01 发布日期:2010-12-01
  • 通讯作者: 邱龙金

Cross validation model for neural network stability

QIU Long-jin1,HE Chang-zheng2   

  1. 1.College of Computer Science,Sichuan University,Chengdu 610065,China
    2.College of Business Administration,Sichuan University,Chengdu 610065,China
  • Received:2010-03-12 Revised:2010-06-17 Online:2010-12-01 Published:2010-12-01
  • Contact: QIU Long-jin

摘要: 根据Skutin提出的交叉验证理论,针对神经网络学习算法提出了神经网络稳定性的交叉验证模型,并选择4种应用广泛、具有代表性的神经网络作为研究对象,通过随机数据集和UCI数据集上的数据实验结果得出了BP、RBF、GRNN、ELM等4种神经网络的稳定性排序,并用统计检验方法对排序结果进行了检验。

Abstract: According to cross-validation theory by Skutin,the cross-validation model of neural network stability is proposed.Four wildly used and representative neural networks are adopted as the subjects investigated and retrieved the rank of the stabilities of BP,RBF,GRNN,ELM,using the experiment results based on the random and UCI data sets.Finally,and the ranking is tested by the statistical method.

中图分类号: