| 新的贝叶斯网络结构学习方法 |
| |
| 引用本文： | 孙岩,唐一源. 新的贝叶斯网络结构学习方法[J]. 计算机工程与设计, 2008, 29(5): 1238-1240 |
| |
| 作者姓名： | 孙岩 唐一源 |
| |
| 作者单位： | 1. 辽宁师范大学,计算机与信息技术学院,辽宁,大连,116029;大连理工大学,神经信息学研究所,辽宁,大连,116023
2. 大连理工大学,神经信息学研究所,辽宁,大连,116023 |
| |
| 摘 要： | 贝叶斯网络是一种将贝叶斯概率方法和有向无环图的网络拓扑结构有机结合的表示模型,它描述了数据项及数据项之间的非线性依赖关系.报告了贝叶斯网络研究的现状,并针对传统算法需要主观规定网络中结点顺序的缺点,提出了一个新的可以在无约束条件下,根据观测得到的训练样本集的概率关系,自动完成学习贝叶斯网络结构的新方法.
|
| 关 键 词： | 贝叶斯网络 贝叶斯概率 无条件约束 有向无环图 结构学习 |
| 文章编号： | 1000-7024(2008)05-1238-03 |
| 修稿时间： | 2007-04-06 |
New algorithm of Bayesian network structure learning |
| |
| SUN Yan,TANG Yi-yuan. New algorithm of Bayesian network structure learning[J]. Computer Engineering and Design, 2008, 29(5): 1238-1240 |
| |
| Authors: | SUN Yan TANG Yi-yuan |
| |
| Affiliation: | SUN Yan1,2,TANG Yi-yuan2(1.College of Computer Science,Liaoning Normal University,Dalian 116029,China,2.Institute of Neuroinformatics,Dalian University of Technology,Dalian 116023,China) |
| |
| Abstract: | Bayesian network is a graphic model that integrates Bayesian probabilistic methods with directed acyclic graphs and describes the probabilistic relationships among variables of interest.A new unconstrained algorithm of Bayesian network structure learning is pre-sented,in which the algorithm can finish automatically the learning of network structure based on the probabilistic relationships from the observed data set. |
| |
| Keywords: | Bayesian belief network Bayesian probabilistic unconstrained conditions directed acyclic graphs structure learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
