EM_GM

An expectation maximization algorithm for learning a multi-dimensional Gaussian mixture.

Although EM algorithm for Gaussian mixture (EM_GM) learning is well known, 3 major MATLAB EM_GM codes are found on the web. However, they either have errors or not easy to incorporate into other MATLAB codes. Therefore, I decide to write my own EM_GM and share it. My EM_GM is designed as a single file function (i.e. all sub functions are included in the same file) for convenience and portability.
Detail descriptions of all inputs and outputs are included in the file. EM_GM can be controlled to plot 1D or 2D problems and display CPU time used as well as number of iterations.

Example:
X = zeros(600,2);
X(1:200,:) = normrnd(0,1,200,2);
X(201:400,:) = normrnd(0,2,200,2);
X(401:600,:) = normrnd(0,3,200,2);
[W,M,V,L] = EM_GM(X,3,[],[],1,[])