| HAL : hal-00375581, version 1 |
| Fiche détaillée | Récupérer au format |
|
|
| XIII International Conference on Applied Stochastic Models and Data Analysis, Vilnius : Lituanie (2009) |
|
|
|
|
| Clustering in Fisher Discriminative Subspaces |
|
|
| Charles Bouveyron 1, 2Camille Brunet 3 |
|
|
| (23/06/2009) |
|
|
| Clustering in high-dimensional spaces is nowadays a recurrent problem in many scientific domains but remains a difficult problem. This is mainly due to the fact that high-dimensional data usually live in low-dimensional subspaces hidden in the original space. This paper presents a model-based clustering approach which models the data in a discriminative subspace with an intrinsic dimension lower than the dimension of the original space. An estimation algorithm, called Fisher-EM algorithm, is proposed for estimating both the mixture parameters and the discriminative subspace. Experiments show that the proposed approach outperforms existing clustering methods and provides a useful representation of the high-dimensional data. |
|
|
|
|
|
|
|
|
|
|
| 1 : | Statistique Appliquée et MOdélisation Stochastique (SAMOS) |
| Université Paris I - Panthéon-Sorbonne | |
| 2 : | Centre d'économie de la Sorbonne (CES) |
| CNRS : UMR8174 – Université Paris I - Panthéon-Sorbonne | |
| 3 : | Informatique, Biologie Intégrative et Systèmes Complexes (IBISC) |
| CNRS : FRE3190 – Université d'Evry-Val d'Essonne | |
|
|
|
|
|
|
|
|
| Domaine | : | Statistiques/Théorie Mathématiques/Statistiques Statistiques/Méthodologie Statistiques/Machine Learning |
|
|
| Model-based clustering – dimension reduction – discriminative subspaces – latent mixture model |
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|
|
| hal-00375581, version 1 | |
| http://hal-paris1.archives-ouvertes.fr/hal-00375581 | |
| oai:hal-paris1.archives-ouvertes.fr:hal-00375581 | |
| Contributeur : Camille Brunet | |
| Soumis le : Mercredi 15 Avril 2009, 15:02:11 | |
| Dernière modification le : Jeudi 16 Avril 2009, 08:34:43 | |