注册 登录  
 加关注
   显示下一条  |  关闭
温馨提示!由于新浪微博认证机制调整,您的新浪微博帐号绑定已过期,请重新绑定!立即重新绑定新浪微博》  |  关闭

罗维的博客

{ 关注机器学习、计算广告、自然语言处理、大规模数据处理等 }

 
 
 
 
 

日志

 
 

Something about Restricted Boltzmann Machines  

2012-03-21 16:59:44|  分类: 机器学习 |  标签: |举报 |字号 订阅

  下载LOFTER 我的照片书  |

罗维


发现一篇介绍Restricted Boltzmann Machines的文章,写得浅显易懂。推荐一下:

http://blog.echen.me/2011/07/18/introduction-to-restricted-boltzmann-machines/

当然他还给出了相应的Python源码:

https://github.com/echen/restricted-boltzmann-machines

作者是目前在Twitter工作的Edwin Chen,他写的博文都不错,值得多学习。

Restricted Boltzmann Machines essentially perform a binary version of factor analysis. (This is one way of thinking about RBMs; there are, of course, others, and lots of different ways to use RBMs, but I’ll adopt this approach for this post.)

More technically, a Restricted Boltzmann Machine is a stochastic neural network (neural network meaning we have neuron-like units whose binary activations depend on the neighbors they’re connected to; stochastic meaning these activations have a probabilistic element)

For example, suppose we have a set of six movies (Harry Potter, Avatar, LOTR 3, Gladiator, Titanic, and Glitter) and we ask users to tell us which ones they want to watch. If we want to learn two latent units underlying movie preferences -- for example, two natural groups in our set of six movies appear to be SF/fantasy (containing Harry Potter, Avatar, and LOTR 3) and Oscar winners (containing LOTR 3, Gladiator, and Titanic), so we might hope that our latent units will correspond to these categories -- then our RBM would look like the following:

 Something about Restricted Boltzmann Machines - vividfree - 做最好的自己

 (Note the resemblance to a factor analysis graphical model.)

上面是对玻尔兹曼机的建模(representation),文中还介绍了State Activation以及Parameter Estimation(Learning weight)方法——approximate gradient descent。最后给出了一些算法层面的改进建议。其实这篇文章写得挺简练,只要理解了,每个人都可以对玻尔兹曼机做个简单的实现。

 

另一方面,研究生院的吴健康老师从图模型的角度,也大致介绍了玻尔兹曼机的内容。

 Something about Restricted Boltzmann Machines - vividfree - 做最好的自己 

我对波尔兹曼机整个模型(representation/inference/learning),目前只是有个大致的了解。不过,它作为从神经网络领域产出的模型,但是又跟概率图模型有一丝的关联,里面还有不少联系点需要去体会。以后会多在这里添上我的感悟。


转载请注明出处:http://luowei828.blog.163.com/
  评论这张
 
阅读(2568)| 评论(0)
推荐 转载

历史上的今天

评论

<#--最新日志,群博日志--> <#--推荐日志--> <#--引用记录--> <#--博主推荐--> <#--随机阅读--> <#--首页推荐--> <#--历史上的今天--> <#--被推荐日志--> <#--上一篇,下一篇--> <#-- 热度 --> <#-- 网易新闻广告 --> <#--右边模块结构--> <#--评论模块结构--> <#--引用模块结构--> <#--博主发起的投票-->
 
 
 
 
 
 
 
 
 
 
 
 
 
 

页脚

网易公司版权所有 ©1997-2017