Accelerating stochastic kernel SOM

Abstract : Analyzing non vectorial data has become a common trend in a number of real-life applications. Various prototype-based methods have been extended to answer this need by means of kernalization that embed data into an (implicit) Euclidean space. One drawback of those approaches is their complexity, which is commonly of order the square or the cube of the number of observations. In this paper, we propose an efficient method to reduce complexity of the stochastic kernel SOM. The results are illustrated on large datasets and compared to the standard kernel SOM. The approach has been implemented in the last version of the R package SOMbrero.
Type de document :
Communication dans un congrès
Michel Verleysen. XXVth European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2017, Bruges, Belgium. d-side publications, pp.269-274, 2017, XXVth European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 〈https://www.elen.ucl.ac.be/esann/〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01516660
Contributeur : Nathalie Villa-Vialaneix <>
Soumis le : mardi 2 mai 2017 - 09:21:15
Dernière modification le : mercredi 10 mai 2017 - 01:08:39
Document(s) archivé(s) le : jeudi 3 août 2017 - 12:29:58

Fichiers

mariette_etal_ESANN2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01516660, version 1

Collections

Citation

Jérôme Mariette, Fabrice Rossi, Madalina Olteanu, Nathalie Villa-Vialaneix. Accelerating stochastic kernel SOM. Michel Verleysen. XXVth European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2017, Bruges, Belgium. d-side publications, pp.269-274, 2017, XXVth European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 〈https://www.elen.ucl.ac.be/esann/〉. 〈hal-01516660〉

Partager

Métriques

Consultations de
la notice

40

Téléchargements du document

31