Quantization based clustering: an iterative approach
Résumé
In this paper we propose a simple new algorithm to perform clustering, based on the Alter algorithm proposed in [5] but lowering signicantly the algorithmic complexity with respect to the number of clusters. An empirical study states the relevance of our iterative process and a confrontation on simulated multivariate and functional data shows the benets of our algorithm.
Domaines
Machine Learning [stat.ML]
Origine : Fichiers produits par l'(les) auteur(s)
Loading...