Supervised and unsupervised classification using mixture models

Stéphane Girard 1 Jerome Saracco 2, 3
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 CQFD - Quality control and dynamic reliability
IMB - Institut de Mathématiques de Bordeaux, Inria Bordeaux - Sud-Ouest
Abstract : This chapter is dedicated to model-based supervised and unsuper-vised classification. Probability distributions are defined over possible labels as well as over the observations given the labels. To this end, the basic tools are the mixture models. This methodology yields a posterior distribution over the labels given the observations which allows to quantify the uncertainty of the classification. The role of Gaussian mixture models is emphasized leading to Linear Discriminant Analysis and Quadratic Discriminant Analysis methods. Some links with Fisher Discriminant Analysis and logistic regression are also established. The Expectation-Maximization algorithm is introduced and compared to the K-means clustering method. The methods are illustrated both on simulated datasets as well as on real datasets using the R software.
Type de document :
Pré-publication, Document de travail
2015
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01241818
Contributeur : Stephane Girard <>
Soumis le : vendredi 11 décembre 2015 - 09:18:25
Dernière modification le : jeudi 29 décembre 2016 - 18:13:08
Document(s) archivé(s) le : samedi 12 mars 2016 - 11:50:14

Fichier

chapClassification-hal.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01241818, version 1

Collections

INSMI | INRIA | IMB | UGA

Citation

Stéphane Girard, Jerome Saracco. Supervised and unsupervised classification using mixture models. 2015. <hal-01241818>

Partager

Métriques

Consultations de
la notice

417

Téléchargements du document

137