The following figure demonstrates Expectation Maximization (EM) [1] for Gaussian Mixtures on the Old Faithful dataset. (Old Faithful is a famous geyser in Yellowstone National Park, US.)
Plotting the waiting time between eruptions over eruption time reveals a "cluster" structure. In this project I model this structure with a Gaussian Mixture Model. To find appriximate cluster centers k-Means Clustering is used. Equations and algorithms can be found in EM_gaussian_mixture.ipynb.
This project is based on an assignment from the lecture Probabilistic Machine Learning at the University of Tübingen.
[1] T. K. Moon. The expectation-maximization algorithm. IEEE Signal processing magazine, 1996.