 |
|
|
|
| HAL : hal-00723989, version 1 |
| DOI : 10.1007/978-3-642-29461-7_9 |
| Fiche détaillée |  Récupérer au format |
|
|
| Belief Functions: Theory and Applications, France (2012) |
|
|
|
|
| Classification trees based on belief functions |
|
|
| Nicolas Sutton Charani 1Sebastien Destercke 1 |
|
|
| (11/05/2012) |
|
|
|
| Decision trees classifiers are popular classification methods. In this paper, we extend to multi-class problems a decision tree method based on belief functions previously described for 2-class problems only. We propose two ways to achieve this extension: combining multiple 2-class trees together and directly extending the estimation of belief functions within the tree to the multi-class setting. We provide experiment results and compare them to classical decision trees. |
|
|
|
|
|
|
|
|
|
|
|
| 1 : | Heuristique et Diagnostic des Systèmes Complexes (HEUDIASYC) |
|
|
|
CNRS : UMR7253 – Université de Technologie de Compiègne |
|
|
|
|
|
|
|
|
|
| Decision et Image |
|
|
|
|
| Domaine | : | Informatique/Apprentissage Informatique/Intelligence artificielle Statistiques/Machine Learning Mathématiques/Statistiques Statistiques/Théorie |
|
|
| Belief functions – Classification – Decision trees |
|
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|||||
|
|
|
| hal-00723989, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00723989 | |
| oai:hal.archives-ouvertes.fr:hal-00723989 | |
| Contributeur : Sébastien Destercke | |
| Soumis le : Jeudi 16 Août 2012, 10:44:47 | |
| Dernière modification le : Jeudi 16 Août 2012, 11:01:27 | |
