inria-00321491, version 2
Self-organization by optimizing free-energy
Jakob Verbeek
1Nikos Vlassis a, 1Ben Krose 1
11th European Symposium on Artificial Neural Networks (ESANN '03) (2003) 125-130
Abstract: We present a variational Expectation-Maximization algorithm to learn probabilistic mixture models. The algorithm is similar to Kohonen's Self-Organizing Map algorithm and not limited to Gaussian mixtures. We maximize the variational free-energy that sums data log-likelihood and Kullback-Leibler divergence between a normalized neighborhood function and the posterior distribution on the components, given data. We illustrate the algorithm with an application on word clustering.
- a – Technical University of Crete
- 1: Instituut voor Informatica (IvI)
- Universiteit van Amsterdam
- Domain : Computer Science/Learning
- Keywords : self-organizing map – mixture modeling – variational EM
- Available versions : v1 (2011-02-03) v2 (2011-03-08)
- inria-00321491, version 2
- http://hal.inria.fr/inria-00321491
- oai:hal.inria.fr:inria-00321491
- From: Jakob Verbeek
- Submitted on: Tuesday, 8 March 2011 15:02:27
- Updated on: Tuesday, 8 March 2011 15:48:12
Associated documents
Export