The Infinite Gaussian Mixture Model

Add to your list(s) Download to your calendar using vCal

• Philipp Hennig (University of Cambridge)
• Friday 20 November 2009, 11:15-12:00
• TCM Seminar Room, Cavendish Laboratory, Department of Physics.

If you have a question about this talk, please contact Emli-Mari Nel.

For this week’s journal club, I would like to re-visit the by now canonical Dirichlet Process Gaussian mixture. The paper can e.g. be found at

http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.111.993&rep=rep1&type=pdf

or, tellingly, at http://www.inference.phy.cam.ac.uk/is/donut/infinite/InfiniteGaussianMixtureModel.ps

Most of us have seen this model before, but many (including myself) have never actually implemented it. I will try to prepare some code, and hope that we will be able to do some actual computing during the session, to understand some of the pitfalls of MCMC inference in this otherwise conceptually very clean model.

This talk is part of the Machine Learning Journal Club series.

This talk is included in these lists:

• Cambridge talks
• Guy Emerson's list
• Hanchen DaDaDash
• Inference Group Journal Clubs
• Inference Group Summary
• Interested Talks
• ML
• Machine Learning Journal Club
• Machine Learning Summary
• Quantum Matter Journal Club
• TCM Seminar Room, Cavendish Laboratory, Department of Physics
• TQS Journal Clubs
• rp587
• yk373's list

Note that ex-directory lists are not shown.