Automatic Derivation of Statistical Algorithms: The EM Family and Beyond
Fischer, Bernd, Schumann, Johann, Buntine, Wray, Gray, Alexander G.
–Neural Information Processing Systems
Machine learning has reached a point where many probabilistic methods can be understood as variations, extensions and combinations of a much smaller set of abstract themes, e.g., as different instances of the EM algorithm. This enables the systematic derivation of algorithms customized for different models.
Neural Information Processing Systems
Dec-31-2003