计算机科学 ›› 2009, Vol. 36 ›› Issue (3): 119-122.

• • 上一篇    下一篇

面向多层次知识表达的贝叶斯分类模型研究

  

  • 出版日期:2018-11-16 发布日期:2018-11-16
  • 基金资助:
    本课题得到国家自然科学基金(60275026)资助.

  • Online:2018-11-16 Published:2018-11-16

摘要: 提出多模式贝叶斯分类算法,由变量值之间的条件独立和条件相关性推断因果关系,根据每个完整随机样本而非整个样本空间构造子模式。结合局部计算近似推理进行概率密度和条件概率分布估计,在此基础上采用后离散化策略自动确定连续变量边界。在UCI机器学习数据集上的实验结果证明了该算法的合理性和有效性。

关键词: 贝叶斯网络 多模式 后离散化策略 局部计算

Abstract: A multi-schema Bayesian classification algorithm was proposed to solve the problem of discretization assumption and graph representation. By reasoning the conditional independence and dependence between attribute values, a submodel was constructed for eac

Key words: Bayesian network, Multi-schema, Post-discretization strategy, Marginal computation

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!