Friday, March 13, 2009

什麼是 EM Algorithm ?

網路上查詢 EM Algorithm在 英文的定義結果:

* An expectation-maximization (EM) algorithm is used in statistics for finding maximum likelihood estimates of parameters in probabilistic models ...
en.wikipedia.org/wiki/Em_algorithm

* The EM Algorithm is a computational tool that uses the method of data augmentation and can be used to optimize a likelihood function in order to ...
hea-www.harvard.edu/AstroStat/statjargon.html

中文名稱是 :最大期望演算法

看一下網友的心得:
EM algorithm

引述一下 :

然後就時光飛逝, EM 跟我的生活毫無瓜葛, 直到今年,
修Statistical theory時,
知道了這是一種求incomplete data MLE的方法,
先在假設參數為已知的某值下,
計算sufficient statistics的期望值 (E-step),
然後假設我們觀察到的資料等於此期望值,
求取使得likelihood極大的參數值 (M-step),
然後不斷地重複這兩步驟(迭代), 直到結果不再變動(收斂),
即求到我們所要的 MLE.




博客來上也有新書有關EM;

The EM Algorithm And Extensions

參考一下嚕:)

No comments:

Post a Comment

發表一下意見,互動一下唄!

LinkWithin

Related Posts Plugin for WordPress, Blogger...

Adventure Book 2.0 Headline Animator

GoogleAd

funP Android 相關文章