CWYAlpha

Just another WordPress.com site

Thought this was cool: [原]浅析Likehood MAP MLE

leave a comment »


举个例子说明Likehood MAP MLE

假定有犯罪团伙A和犯罪团伙B。

假定我们的概念有

h{

h1: 所抓得人是团伙A的

h2: 所抓得人是团伙B的

….

}

如果我们抓到了一票人是a1,a2,…an,那么这伙人是团伙A还是团伙B?

即求解P( h|D={a1,a2,…an} )?

假定从案底显示,团伙A有10个人,团伙B有20个人,团伙A被抓到的概率是50%,团伙B被抓到的概率是80%。

         p(h1)  = 50%

         p(h2)  = 80%

已知在清华东门抓了2个人,那么这两个人最大可能性是来自哪个团伙的?

likelyhood: 

P(D|h1) = 1/10*1/9   (团伙A产生两个人)

P(D|h2) = 1/20*1/19  (团伙B产生两个人)

   

h^MAP = argmax P(D|h)*p(h)

                    h

P(D|h1)P(h1) =   1/10*1/9*50% =      0.0055

P(D|h2)P(h2) =   1/20*1/19*10% =     0.0003

h^MAP = 0.0055

h^MLE = argmax P(D|h)

                    h

P(D|h3) =   1/10*1/9 =      0.0111

P(D|h4) =   1/20*1/19 =      0.0026

h^MLE = 0.0111

因此,如果已知抓到两个人,那么这两个人更有可能是来自团伙A。

  

作者:pennyliang 发表于2013-3-20 10:50:49 原文链接
阅读:146 评论:0 查看评论

from pennyliang的专栏: http://blog.csdn.net/pennyliang/article/details/8694037

Written by cwyalpha

四月 11, 2013 在 3:53 上午

发表在 Uncategorized

发表评论

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / 更改 )

Twitter picture

You are commenting using your Twitter account. Log Out / 更改 )

Facebook photo

You are commenting using your Facebook account. Log Out / 更改 )

Google+ photo

You are commenting using your Google+ account. Log Out / 更改 )

Connecting to %s

%d 博主赞过: