压缩候选的贝叶斯信念网络构造算法

Algorithm of Bayesian Belief Network Structure of Compressed Candidature

关键词:  贝叶斯信念网络  压缩候选  算法  数据挖掘

Key words:  Bayesian belief network  compressed candidature  algorithm  data mining

摘要:

针对传统算法分类速度较慢的不足,改进传统算法中候选变量的搜索方式,提出用依赖度量函数测量变量之间的依赖程度,得出压缩候选的贝叶斯信念网络构造算法.该算法在不影响原有算法可靠性的前提下,提高了学习速度.

Abstract:

A learning algorithm of compressed candidates based on Bayesia belief network is developed to solve slow running problem of traditional Bayesian belief network constructing algorithm.The improved method for searching candidates with a modified dependence measure is used in the presented algorithm which can speed up the study process without sacrificing the reliability of the traditional method.