Efficient greedy learning of Gaussian mixtures - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2001

Efficient greedy learning of Gaussian mixtures

Jakob Verbeek
Nikos Vlassis
  • Function : Author
  • PersonId : 853678
Ben Krose
  • Function : Author
  • PersonId : 853721


We present a deterministic greedy method to learn a mixture of Gaussians. The key element is that we build-up the mixture component-wise: we start with one component and then add new components one at a time and update the mixtures in between the component insertions. Instead of solving directly a optimization problem involving the parameters of all components, we replace the problem by a sequence of component allocation problems involving only the parameters of the new component. Included are experimental results obtained from extensive tests on artificially generated data sets. The new learning method is compared with the standard EM with random initializations approach as well as to other existing approaches to learning Gaussian mixtures.
Fichier principal
Vignette du fichier
verbeek01bnaic.pdf (168.9 Ko) Télécharger le fichier
Vignette du fichier
VVK01b.png (22.22 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

inria-00321510 , version 1 (16-02-2011)


  • HAL Id : inria-00321510 , version 1


Jakob Verbeek, Nikos Vlassis, Ben Krose. Efficient greedy learning of Gaussian mixtures. The 13th Belgian-Dutch Conference on Artificial Intelligence (BNAIC'01), Oct 2001, Amsterdam, Netherlands. pp.251--258. ⟨inria-00321510⟩
68 View
79 Download


Gmail Facebook Twitter LinkedIn More