Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (16): 39-41.DOI: 10.3778/j.issn.1002-8331.2010.16.011

• 研究、探讨 • Previous Articles     Next Articles

Structure learning method of Bayesian network with uncertain prior information

WANG Lei,LIU Ming-hui,WANG Wei-ping   

  1. College of Information Systems and Management,National University of Defense Technology,Changsha 410073,China
  • Received:2008-12-15 Revised:2009-03-10 Online:2010-06-01 Published:2010-06-01
  • Contact: WANG Lei


王 磊,刘明辉,王维平   

  1. 国防科技大学 信息系统与管理学院,长沙 410073
  • 通讯作者: 王 磊

Abstract: A structure learning method of Bayesian network is presented to solve the problem of structure learning with uncertain prior information.A description method of the uncertain prior information is given.An improved MDL score method named SMDL is proposed to fuse the prior information in learning process.Simulated annealing method is used to solve the problem.This method is validated by experiments.

摘要: 针对先验信息不确定条件下的贝叶斯网络学习问题,提出了一种非确定先验结构信息贝叶斯网络的结构学习方法。主要在以下几个方面开展了工作:提出了一种贝叶斯网络结构的不确定先验信息表示方法;改进了MDL测度,提出了SMDL测度,使之能在学习过程中考虑先验信息的不确定性;基于模拟退火算法,对问题进行求解。最后通过实验对算法的可行性进行了验证。

CLC Number: