The generative self-organizing map: a probabilistic generalization of Kohonen's SOM

Abstract : We present a variational Expectation-Maximization algorithm to learn proba- bilistic mixture models. The algorithm is similar to Kohonen's Self-Organizing Map algorithm and can be applied on any mixture model for which we can find a standard Expectation Maximization algorithm. We maximize the variational free- energy which sums data log-likelihood and Kullback-Leibler divergence between the neighborhood function and the posterior distribution on the components, given data. We illustrate the algorithm with an application on word clustering.
Document type :
Reports
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download


https://hal.inria.fr/inria-00321505
Contributor : Jakob Verbeek <>
Submitted on : Wednesday, February 16, 2011 - 5:09:33 PM
Last modification on : Monday, September 25, 2017 - 10:08:04 AM
Long-term archiving on : Tuesday, May 17, 2011 - 2:34:55 AM

Files

verbeek02tr.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00321505, version 1

Collections

Citation

Jakob Verbeek, Nikos Vlassis, Ben Krose. The generative self-organizing map: a probabilistic generalization of Kohonen's SOM. [Technical Report] IAS-UVA-02-03, 2002. ⟨inria-00321505⟩

Share

Metrics

Record views

272

Files downloads

735