首页> 外文学位 >An information theory based approach to structure learning in Bayesian networks.

【24h】

An information theory based approach to structure learning in Bayesian networks.

机译：贝叶斯网络中基于信息论的结构学习方法。

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Structure learning of Bayesian networks is a well-researched but computationally hard task. We present an algorithm that adopts an information theory based approach to learn structures of bayesian networks. Our algorithm also makes use of basic bayesian network concepts like D-separation and markov independence. We show that the proposed algorithm is capable of handling networks with a large number of variables. We present the applicability of the proposed algorithm on four datasets and also compare its performance and computational efficiency with other standard structure learning methods (Hill climbing, MCMC).

机译：贝叶斯网络的结构学习是一项经过充分研究但计算困难的任务。我们提出一种算法，该算法采用基于信息论的方法来学习贝叶斯网络的结构。我们的算法还利用了基本的贝叶斯网络概念，例如D分离和Markov独立性。我们证明了所提出的算法能够处理具有大量变量的网络。我们介绍了该算法在四个数据集上的适用性，还将其性能和计算效率与其他标准结构学习方法（希尔攀岩，MCMC）进行了比较。

著录项

作者
Anantha, Gopalakrishna.;
展开▼
作者单位

University of Kansas.;

展开▼
授予单位 University of Kansas.;
学科 Engineering Electronics and Electrical.
学位 M.S.
年度 2006
页码 93 p.
总页数 93
原文格式 PDF
正文语种 eng
中图分类无线电电子学、电信技术;
关键词

相似文献

外文文献
中文文献
专利

1. Implementing statistical learning methods through Bayesian networks. Part 1: A guide to Bayesian parameter estimation using forensic science data [J] . A. Biedermann, F. Taroni, S. Bozza Forensic science international . 2010,第1a3期

机译：通过贝叶斯网络实施统计学习方法。第1部分：使用法医学数据进行贝叶斯参数估计的指南
2. An improved evolutionary approach-based hybrid algorithm for Bayesian network structure learning in dynamic constrained search space [J] . Neural computing & applications . 2020,第5期

机译：一种改进的基于进化方法的动态约束搜索空间中贝叶斯网络结构学习的混合算法
3. Histogram distance-based Bayesian Network structure learning: A supervised classification specific approach [J] . B. Sierra, E. Lazkano, E. Jauregi, Decision support systems . 2009,第1期

机译：基于直方图距离的贝叶斯网络结构学习：一种监督分类的特定方法
4. Learning Bayesian networks. I. A theory based on MAP-MDL criteria [C] . Heping Pan Information Fusion, 2002. Proceedings of the Fifth International Conference on . 2002

机译：学习贝叶斯网络。一，基于MAP-MDL标准的理论
5. Design patterns for online learning environments: A structured approach for operationalizing and sharing theory-based design knowledge. [D] . Le, Andrew Phong. 2006

机译：在线学习环境的设计模式：一种用于操作和共享基于理论的设计知识的结构化方法。
6. An efficient Bayesian approach for Gaussian Bayesian network structure learning [O] . Shengtong Han, Hongmei Zhang, Ramin Homayouni, -1

机译：高斯贝叶斯网络结构学习的有效贝叶斯方法
7. Learning Bayesian networks from data: An information-theory based approach [O] . Cheng, J., Greiner, R., Kelly, J., 2002

机译：从数据中学习贝叶斯网络：一种基于信息理论的方法

An information theory based approach to structure learning in Bayesian networks.

摘要

著录项

相似文献

相关主题

期刊订阅