计算机与数字工程2017，Vol.45Issue(4)：640-644,5.DOI:10.3969/j.issn.1672-9722.2017.04.010
基于无限逆狄利克雷混合模型的变分学习
Variational Learning Based on Infinite Inverted Dirichlet Mixture Model
摘要
Abstract
Recent studies have shown that finite inverse Dirichlet mixture model is an important model for modeling non Gauss data.However, it has the problem of parameter estimation and model selection.The EM algorithm can not be used to accurately estimate the parameters and select the optimal number of mixture components.Therefore, this paper studies the infinite inverse Dirichlet mixture model, presents a novel variational approximate inference algorithm for learning.The algorithm can solve these two problems at the same time.In order to verify the effectiveness of the algorithm, this paper carries out experiments on artificial data sets.Experimental results show that the variational Bayesian inference to estimate mixed infinite inverse Dirichlet distribution is a very effective method.关键词
逆狄利克雷/变分推理/贝叶斯估计/参数估计/模型选择Key words
inverted Dirichlet/variational inference/Bayesian estimation/parameter estimation/model selection分类
信息技术与安全科学引用本文复制引用
王景中,尉朋朋..基于无限逆狄利克雷混合模型的变分学习[J].计算机与数字工程,2017,45(4):640-644,5.基金项目
国家自然科学基金(编号:61371142) （编号:61371142）
北方工业大学校内专项(编号:XN060)资助. （编号:XN060）
