基于因果语义定向的贝叶斯网络结构学习  

Learning Bayesian networks structure based on causal semanitics orienting

作　　者：王双成[1] 张明[1] 陈乃激[1] 

机构地区：[1]上海立信会计学院信息科学系

出　　处：《计算机工程与应用》2007年第8期29-31,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.60675036);上海市重点学科(No.P1601);上海市教委重点项目(No.05zz66)

摘　　要：基于变量之间基本依赖关系、基本结构、d-separation标准、依赖分析思想和混合定向策略,给出了一种有效实用的贝叶斯网络结构学习方法,不需要结点有序,并能避免打分-搜索方法存在的指数复杂性,以及现有依赖分析方法的大量高维条件概率计算等问题。A new method of learning Bayesian network structure based on basic dependency relationship between variables,basic structure between nodes,d-separation criterion,the idea of dependency analysis and the strategy of mixture orienting is given.This method do not need sorting nodes.h can effectively avoid the exponential complexity of search ＆ scoring based methods and a large number of the calculate of high rank conditional probability in existing dependency analysis based methods.

关 键 词：贝叶斯网络 结构学习 依赖分析 因果语义 碰撞识别 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]