Large datasets: a mixed method to adapt and improve their learning by neural networks used in regression contexts

Marc Sauget 1 Julien Henriet 1 Michel Salomon 2 Sylvain Contassot-Vivier 3
1 ENISYS/IRMA
FEMTO-ST - Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies
2 AND
FEMTO-ST - Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies
3 ALGORILLE - Algorithms for the Grid
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : The purpose of this work is to further study the relevance of accelerating the Monte-Carlo calculations for the gamma rays external radiotherapy through feed-forward neural networks. We have previously presented a parallel incremental algorithm that builds neural networks of reduced size, while providing high quality approximations of the dose deposit~\cite{Vecpar08b}. Our parallel algorithm consists in an optimized decomposition of the initial learning dataset (also called learning domain) in as much subsets as available processors. However, although that decomposition provides subsets of similar signal complexities, their sizes may be quite different, still implying potential differences in their learning times. This paper presents an efficient data extraction allowing a good and balanced training without any loss of signal information. As will be shown, the resulting irregular decomposition permits an important improvement in the learning time of the global network.
Type de document :
Communication dans un congrès
Lazaros Iliadis; Chrisina Jayne. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-363 (Part I), pp.182-191, 2011, Engineering Applications of Neural Networks. 〈10.1007/978-3-642-23957-1_21〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00643870
Contributeur : Sylvain Contassot-Vivier <>
Soumis le : mercredi 2 août 2017 - 11:47:13
Dernière modification le : jeudi 11 janvier 2018 - 06:27:05

Fichier

978-3-642-23957-1_21_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Marc Sauget, Julien Henriet, Michel Salomon, Sylvain Contassot-Vivier. Large datasets: a mixed method to adapt and improve their learning by neural networks used in regression contexts. Lazaros Iliadis; Chrisina Jayne. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-363 (Part I), pp.182-191, 2011, Engineering Applications of Neural Networks. 〈10.1007/978-3-642-23957-1_21〉. 〈hal-00643870〉

Partager

Métriques

Consultations de la notice

413

Téléchargements de fichiers

10