Recursive unsupervised learning of finite mixture models
Related Experiment Videos
Zoran Zivkovic1, Ferdinand van der Heijden
1Laboratory for Measurement and Instrumentation, University of Twente, Enschede, The Netherlands. zivkovic@science.uva.nl
Abstract:
There are two open problems when finite mixture densities are used to model multivariate data: the selection of the number of components and the initialization. In this paper, we propose an online (recursive) algorithm that estimates the parameters of the mixture and that simultaneously selects the number of components. The new algorithm starts with a large number of randomly initialized components. A prior is used as a bias for maximally structured models. A stochastic approximation recursive learning algorithm is proposed to search for the maximum a posteriori (MAP) solution and to discard the irrelevant components.
Related Concept Videos
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Law of Independent Assortment
Methods of Medium Optimization
Racemic Mixtures and the Resolution of Enantiomers