An Entropy criterion for assessing the number of clusters in a mixture model - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 1993

An Entropy criterion for assessing the number of clusters in a mixture model

Gilles Celeux
  • Function : Author
  • PersonId : 833415
G. Soromenho
  • Function : Author

Abstract

In this paper, we consider an entropy criterion to estimate the number of clusters arising from a mixture model. This criterion is derived from a relation linking the likelihood and the classification likelihood of a mixture. Its performances are investigated through Monte-Carlo numerical experiments and show favourable results as compared with other classical criteria.

Domains

Other [cs.OH]
Fichier principal
Vignette du fichier
RR-1874.pdf (650.55 Ko) Télécharger le fichier

Dates and versions

inria-00074799 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00074799 , version 1

Cite

Gilles Celeux, G. Soromenho. An Entropy criterion for assessing the number of clusters in a mixture model. RR-1874, INRIA. 1993. ⟨inria-00074799⟩
363 View
3494 Download

Share

Gmail Facebook Twitter LinkedIn More