基于信息论的Bayesian网络结构学习算法研究

Bayesian网是一种进行不确定性推理的有力工具,它结合图型理论和概率理论,可以方便地表示和计算我们感兴趣的事件概率,同时也是对实体之间依赖关系提供了一种紧凑、直观、有效的图形表示。文中基于信息论中测试信息独立理论,对Bayesian网中各结点进行条件独立(CI)测试,以发现各结点的条件依赖关系,并通过计算结点之间的互相依赖度以发现Bayesian网边的方向,从而构造Bayesian网结构,算法的计算复杂度只需要进行O(N²)次CI测试。

Algorithm of Bayesian network structural learning based on information theory

Bayesian network is a forceful tool to practise inference of uncertainty. It combines graphic theories and probability ones, which can conveniently express and calculate the probability of interesting events and at the same time provide a compact, visual and effective graphic expression for the dependant relationship among the entities. On the basis of testing information independence theory, the test of CI(conditional independence) was carried out on all the joints in the Bayesian network to find out the conditionally dependant relations among them. Then an effective algorithm of Bayesian network structural learning was worked out, which only needed CI testing of O(N~2) times.