Fast Algorithm and Implementation of Dissimilarity Self-Organizing Maps

Abstract : In many real world applications, data cannot be accurately represented by vectors. In those situations, one possible solution is to rely on dissimilarity measures that enable sensible comparison between observations. Kohonen's Self-Organizing Map (SOM) has been adapted to data described only through their dissimilarity matrix. This algorithm provides both non linear projection and clustering of non vector data. Unfortunately, the algorithm suffers from a high cost that makes it quite difficult to use with voluminous data sets. In this paper, we propose a new algorithm that provides an important reduction of the theoretical cost of the dissimilarity SOM without changing its outcome (the results are exactly the same as the ones obtained with the original algorithm). Moreover, we introduce implementation methods that result in very short running times. Improvements deduced from the theoretical cost model are validated on simulated and real world data (a word list clustering problem). We also demonstrate that the proposed implementation methods reduce by a factor up to 3 the running time of the fast algorithm over a standard implementation.
Type de document :
Article dans une revue
Neural Networks, Elsevier, 2006, 19 (6-7), pp.855-863. 〈10.1016/j.neunet.2006.05.002〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger
Contributeur : Fabrice Rossi <>
Soumis le : vendredi 21 septembre 2007 - 16:59:53
Dernière modification le : mercredi 17 octobre 2018 - 09:54:02
Document(s) archivé(s) le : vendredi 9 avril 2010 - 02:38:47


Fichiers produits par l'(les) auteur(s)




Brieuc Conan-Guez, Fabrice Rossi, Aïcha El Golli. Fast Algorithm and Implementation of Dissimilarity Self-Organizing Maps. Neural Networks, Elsevier, 2006, 19 (6-7), pp.855-863. 〈10.1016/j.neunet.2006.05.002〉. 〈inria-00174196〉



Consultations de la notice


Téléchargements de fichiers