通过空间的稀疏日志高斯过程流行病学方法Sparse Log Gaussian Processes via MCMC for Spatial Epidemiology |
|
课程网址: | http://videolectures.net/gpip06_vanhatalo_slgpv/ |
主讲教师: | Jarno Vanhatalo |
开课单位: | 阿尔托大学 |
开课时间: | 2007-02-25 |
课程语种: | 英语 |
中文简介: | 对数高斯过程(LGP)是一种有吸引力的方式来构建强度表面的目的,空间流行病学。通过在相对对数泊松率之前放置gp,强度表面自然平滑。在这项工作中,一个完全独立的训练条件(FITC)稀疏近似被用来加速gp计算。考虑到近似条件后验精度,通过变换加快了潜在值的采样。 |
课程简介: | Log Gaussian processes (LGP) are an attractive manner to construct intensity surfaces for the purposes of spatial epidemiology. The intensity surfaces are naturally smoothed by placing a GP prior over the relative log Poisson rate. In this work a fully independent training conditional (FITC) sparse approximation is used to speed up GP computations. The sampling of the latent values is sped up with transformations taking into account the approximate conditional posterior precision. |
关 键 词: | 日志高斯过程; 流行病学; 对数泊松比 |
课程来源: | 视频讲座网 |
最后编审: | 2021-01-31:nkq |
阅读次数: | 50 |