| 期望最大算法及其应用(1) |
| |
| 引用本文： | 李昌利,沈玉利.期望最大算法及其应用(1)[J].计算机工程与应用,2008,44(29):61-64. |
| |
| 作者姓名： | 李昌利 沈玉利 |
| |
| 作者单位： | 广东海洋大学信,息学院,广东,湛江,524088 |
| |
| 基金项目： | 广东省自然科学基金，广东省科技厅科技计划 |
| |
| 摘 要： | EM算法是实现极大似然估计的一种有效方法,主要用于非完全数据的参数估计。它通过假设隐变量的存在,极大地简化了似然方程;对于一些特殊的参数估计问题,利用EM算法也很容易实现。而极大似然估计是一种常用的参数估计方法,EM算法使其应用更加广泛。文章从应用者的角度出发,内容是自包含的。
|
| 关 键 词： | 期望最大(EM) 极大似然估计(MLE) 不完全数据 隐变量 |
| 收稿时间： | 2007-11-20 |
| 修稿时间： | 2008-1-14
|
Tutorial of EM algorithm and its application:part I |
| |
| LI Chang-li,SHEN Yu-li.Tutorial of EM algorithm and its application:part I[J].Computer Engineering and Applications,2008,44(29):61-64. |
| |
| Authors: | LI Chang-li SHEN Yu-li |
| |
| Affiliation: | School of Information Engineering，Guangdong Ocean University，Zhanjiang，Guangdong 524088，China |
| |
| Abstract: | EM algorithm is an effective method for maximum-likelihood estimate(MLE),which is mainly used to estimate parameters of incomplete data.On the one hand,by assuming the existence of hidden variable in EM algorithm,the likelihood function are greatly simplified;on the other hand,some special parameters estimation can be easily realized by virtue of EM algorithm.MLE is a common parameters estimation method and EM algorithm makes its application more extensive.This tutorial is organized from users' points of view and its content is self-contained. |
| |
| Keywords: | expectation-maximization(EM) maximum likelihood estimation(MLE) incomplete data hidden variable |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
