File Exchange

image thumbnail

Dirichlet Process Gaussian Mixture Model

version 1.0.0.0 (6.29 KB) by Mo Chen
Dirichlet Process Gaussian Mixture Model aka Infinite GMM using Gibbs Sampling

6 Downloads

Updated 13 Mar 2016

View License

This package solves the Dirichlet Process Gaussian Mixture Model (aka Infinite GMM) with Gibbs sampling. This is nonparametric Bayesian treatment for mixture model problems which automatically selects the proper number of the clusters.
I includes the Gaussian component distribution in the package. However, the code is flexible enough for Dirichlet process mixture model of any distribution. User can write your own class for the base distribution then let the underlying Gibbs sampling engine do the inference work.
Please try the demo script in the package.

This package is now a part of the PRML toolbox (http://www.mathworks.com/matlabcentral/fileexchange/55826-pattern-recognition-and-machine-learning-toolbox).

Comments and Ratings (7)

Jack Ma

Is there any detail description of the algorithm, just like you did for Variational Bayesian Inference for Gaussian Mixture Model?

David Duan

yuebin wang

Rini

Is it applicable for 1D data as well?

Updates

1.0.0.0

update description

MATLAB Release Compatibility
Created with R2016a
Compatible with any release
Platform Compatibility
Windows macOS Linux