贝塔过程先验的非参数因子分析Nonparametric Factor Analysis with Beta Process Priors |
|
课程网址: | http://videolectures.net/icml09_paisley_nfa/ |
主讲教师: | John Paisley |
开课单位: | 杜克大学 |
开课时间: | 2009-09-17 |
课程语种: | 英语 |
中文简介: | 我们使用beta过程先验提出了因子分析问题的非参数扩展。该β过程因子分析(BPFA)模型允许将数据集分解为稀疏因子集的线性组合,提供关于观察的基础结构的信息。与Dirichlet过程一样,β过程是一个完全贝叶斯共轭先验,它允许进行分析后验计算和直接推理。我们推导出变分贝叶斯推理算法,并在MNIST数字和HGDP CEPH细胞系面板数据集上演示该模型。 |
课程简介: | We propose a nonparametric extension to the factor analysis problem using a beta process prior. This beta process factor analysis (BPFA) model allows for a dataset to be decomposed into a linear combination of a sparse set of factors, providing information on the underlying structure of the observations. As with the Dirichlet process, the beta process is a fully Bayesian conjugate prior, which allows for analytical posterior calculation and straightforward inference. We derive a variational Bayes inference algorithm and demonstrate the model on the MNIST digits and HGDP-CEPH cell line panel datasets. |
关 键 词: | 因子分析; 非参数扩展; 线性组合 |
课程来源: | 视频讲座网 |
最后编审: | 2019-04-24:cwx |
阅读次数: | 245 |