Bayesian feature weighting for unsupervised learning, with application to object recognition

Abstract : We present a method for variable selection/weighting in an unsupervised learning context using Bayesian shrinkage. The basis for the model parameters and cluster assignments can be computed simultaneous using an efficient EM algorithm. Applying our Bayesian shrinkage model to a complex problem in object recognition (Duygulu, Barnard, de Freitas and Forsyth 2002), our experiments yied good results.
Keywords : LEAR
Type de document :
Communication dans un congrès
Christopher M. Bishop and Brendan J. Frey. Artificial Intelligence and Statistics (AI & Statistics '03), Jan 2003, Key West, United States. Society for Artificial Intelligence and Statistics, 2003, 〈http://research.microsoft.com/en-us/um/cambridge/events/aistats2003/proceedings/papers.htm〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548235
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 14:51:34
Dernière modification le : lundi 20 décembre 2010 - 15:28:45
Document(s) archivé(s) le : lundi 21 mars 2011 - 02:46:41

Fichier

shrinkage.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00548235, version 1

Citation

Peter Carbonetto, Nando De Freitas, Paul Gustafson, Natalie Thompson. Bayesian feature weighting for unsupervised learning, with application to object recognition. Christopher M. Bishop and Brendan J. Frey. Artificial Intelligence and Statistics (AI & Statistics '03), Jan 2003, Key West, United States. Society for Artificial Intelligence and Statistics, 2003, 〈http://research.microsoft.com/en-us/um/cambridge/events/aistats2003/proceedings/papers.htm〉. 〈inria-00548235〉

Partager

Métriques

Consultations de la notice

108

Téléchargements de fichiers

74