MONNA: A multiple ordinate neural network architecture

Abstract : This article aims at showing an architecture of neural networks designed for the classification of data distributed among a high number of classes. A significant gain in the global classification rate can be obtained using our architecture. This latter is based on a set of several little neural networks, each one discriminating only two classes. The specialization of each neural network simplifies their structure and improves the classification. Moreover, the learning determines automatically the number of hidden neurons. The discussion is illustrated by tests on data bases from the UCI machine learning database repository. The experimental results show that this architecture can achieve a faster learning, simpler neural networks and an improved performance in classification.
Type de document :
Communication dans un congrès
EIS'2000, Jun 2000, Paisley, United Kingdom. 1, pp.47-53, 2000
Liste complète des métadonnées
Contributeur : Image Greyc <>
Soumis le : jeudi 28 mars 2013 - 14:13:19
Dernière modification le : mardi 5 juin 2018 - 10:14:42
Document(s) archivé(s) le : dimanche 2 avril 2017 - 22:04:19


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


  • HAL Id : hal-00805620, version 1


Olivier Lezoray, Hubert Cardot, Dominique Fournier, Marinette Revenu. MONNA: A multiple ordinate neural network architecture. EIS'2000, Jun 2000, Paisley, United Kingdom. 1, pp.47-53, 2000. 〈hal-00805620〉



Consultations de la notice


Téléchargements de fichiers