ML estimation of parameters of Gaussian Mixture Models with carefully implemented EM algorithm.
by Alesis Novik for Shogun Machine Learning Toolbox (Technical University Berlin / Max Planck Campus Tübingen)
The Expectation-Maximization algorithm is well known in the machine learning community. The goal of the project will be a robust implementation of the Expectation-Maximization algorithm for Gaussian Mixture Models within the Shogun Machine Learning Toolbox. Computational tricks and techniques will be used to overcome computational problems inherent within the algorithm.