Difference between revisions of "10-601 Topic Models"
From Cohen Courses
Jump to navigationJump to search| (One intermediate revision by the same user not shown) | |||
| Line 9: | Line 9: | ||
=== Readings === | === Readings === | ||
| − | * | + | * Murphy ch 27.3 (don't read 27.3.6) and 27.4. |
| − | * LDA is not covered in Mitchell. There's a nice [http://www.cs.princeton.edu/~blei/papers/Blei2012.pdf overview paper on LDA] by David Blei. | + | * LDA is not covered in Mitchell. There's a nice [http://www.cs.princeton.edu/~blei/papers/Blei2012.pdf overview paper on LDA] by David Blei. |
* Here's the [http://www.cs.cmu.edu/~wcohen/10-601/lda-demo code I discussed in class] and some sample data. | * Here's the [http://www.cs.cmu.edu/~wcohen/10-601/lda-demo code I discussed in class] and some sample data. | ||
| + | * [https://en.wikipedia.org/wiki/Dirichlet-multinomial_distribution The Dirichlet-multinomial page on wikipedia] has a good discussion of collapsed Gibbs sampling. | ||
=== Summary === | === Summary === | ||
Latest revision as of 16:35, 4 April 2016
This a lecture used in the Syllabus for Machine Learning 10-601B in Spring 2016
Poll: https://piazza.com/class/ij382zqa2572hc
Slides
Readings
- Murphy ch 27.3 (don't read 27.3.6) and 27.4.
- LDA is not covered in Mitchell. There's a nice overview paper on LDA by David Blei.
- Here's the code I discussed in class and some sample data.
- The Dirichlet-multinomial page on wikipedia has a good discussion of collapsed Gibbs sampling.
Summary
You should know:
- what Gibbs sampling is, and how it can be used for inference in a directed graphical model.
- what graphical models are associated with supervised naive Bayes, unsupervised naive Bayes, and LDA.
