 |
 |
SAMM - Statistique, Analyse, Modélisation Multidisciplinaire |  |
|
|
SAMM - Statistique, Analyse, Modélisation Multidisciplinaire | |
| HAL: hal-00692282, version 1 |
| arXiv: 1204.6509 |
| Detailed view |  Export this paper |
 |
| 20-th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2012), Bruges : Belgique (2012) |
|
|
|
|
| Dissimilarity Clustering by Hierarchical Multi-Level Refinement |
|
|
| Brieuc Conan-Guez 1Fabrice Rossi 2 |
|
|
| (2012-04) |
|
|
|
| We introduce in this paper a new way of optimizing the natural extension of the quantization error using in k-means clustering to dissimilarity data. The proposed method is based on hierarchical clustering analysis combined with multi-level heuristic refinement. The method is computationally efficient and achieves better quantization errors than the relational k-means |
|
|
|
|
|
|
|
|
|
|
|
| 1: | Laboratoire d'Informatique Théorique et Appliquée (LITA) |
|
|
|
Université Paul Verlaine - Metz |
|
|
| 2: | Statistique, Analyse et Modélisation Multidisciplinaire (SAmos-Marin Mersenne) (SAMM) |
|
|
|
Université Paris I - Panthéon-Sorbonne |
|
|
|
|
|
|
|
|
|
| Subject | : | Statistics/Machine Learning Computer Science/Learning |
|
|
| Attached file list to this document: | |||||||||||||
|
|||||||||||||
|
|
|
| hal-00692282, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00692282 | |
| oai:hal.archives-ouvertes.fr:hal-00692282 | |
| From: Fabrice Rossi | |
| Submitted on: Sunday, 29 April 2012 18:15:12 | |
| Updated on: Thursday, 10 May 2012 16:50:09 | |
