期刊文献+

基于贝叶斯网络的概率图模型变分近似推理研究 被引量:2

Variational Approximate Reasoning for Probabilistic Graph Models Based on Bayesian Networks
下载PDF
导出
摘要 概率图模型利用了概率论和图论的关键内容,为解决多变量关系中所存在的依赖性与复杂性提供了完整的解决路径。在语言处理、计算机视觉、计算生物学等众多领域得到广泛应用。本文以贝叶斯网络作为核心研究方向,就概率图模型变分近似推理的全局性、收敛性、单调性等诸多特征进行辩证分析。最终论述了基于贝叶斯网络的概率图模型变分近似推理算法的应用范畴和优势,以便为相关研究提供理论参考。 Probabilistic graph models use the key content of probability theory and graph theory to provide a complete solution to the dependence and complexity existing in multivariate relations.It has been widely used in many fields such as language processing,computer vision, computational biology and so on.This paper takes the Bayesian network as the core research direction,and conducts a dialectical analysis on the global,convergence and monotonic characteristics of the variational approximate reasoning of the probability map model.Finally,the application category and advantages of variational approximate reasoning algorithm based on Bayesian network probability model are discussed in order to provide theoretical reference for related research.
作者 何林海 He Lin-hai(Xiangtan Medical and Health Vocational College Hunan Xiangtan 411102)
出处 《山东农业工程学院学报》 2019年第4期26-27,共2页 The Journal of Shandong Agriculture and Engineering University
基金 湖南省教育科学规划课题为公办高职院校混合所有制二级学院体制机制建设研究,课题编号为XJK17CZY097
关键词 贝叶斯网络 概率图模型 变分近似推理 Bayesian network Probability map model Variational approximate reasoning
  • 相关文献

参考文献3

二级参考文献199

  • 1Daly R, Shen Q, Aitken S. Learning Bayesian Networks: Approa?ches and Issues. Knowledge Engineering Review, 2011, 26 ( 2 ) : 99-157.
  • 2PearlJ. Probabilistic Reasoning in Intelligent Systems: Networksof Plausible Inference. San Francisco, USA: Morgan Kaufmann, 1988.
  • 3Dagum P, Luby M. Approximating Probabilistic Inference in Baye?sian Belief Networks is NP-Hard. Artificial Intelligence, 1993, 60 (1): 141...:153.
  • 4Takaishi T. Bayesian Inference of Stochastic Volatility Model by Hy?brid Monte Carlo.Journal of Circuits, Systems and Computers, 2009,18(8): 1381-1396.
  • 5Draper D. Clustering without (Thinking about) Triangulation II Proc of the 11 th Conference on Uncertainty in Artificial Intelligence. Montreal, Canada, 1995: 378-385.
  • 6Tsamardinos I, Aliferis C F. Towards Principled Feature Selection: Relevancy, Filters and Wrappers[EB/OLJ.[2012 - 05 - 01J. http://research. microsoft. coml enus/uml cambridgel eventsl aistats 2003/proceedings/133. pdf.
  • 7Jin K H, Wu Dan, Wu Libing. On Designing Approximate Infer?ence Algorithms for Multiply Sectioned Bayesian Networks II Proc of the IEEE International Conference on Granular Computing. Nan?chang, China, 2009: 294 - 299.
  • 8Neal R M. Probabilistic Inference Using Markov Chain Monte Carlo Methods[EB/OLJ.[2012-05-01J. http://www. cs. toronto. edu/ publ radfordl review. pdf.
  • 9Yu Binbing. A Bayesian MCMC Approach to Survival Analysis with Doubly-Censored Data. Computational Statistics and Data Analy?sis, 2010, 54(8): 1921-1929.
  • 10Geman S, Geman D. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. IEEE Trans on Pattern Analysis and Machine Intelligence, 1984, 6 (6) : 721-741.

共引文献10

同被引文献21

引证文献2

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部