Optimising the topology of complex neural networks

Fei Jiang 1, 2 Hugues Berry 2 Marc Schoenauer 1
1 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France, X - École polytechnique, CNRS - Centre National de la Recherche Scientifique : UMR7161
2 ALCHEMY - Architectures, Languages and Compilers to Harness the End of Moore Years
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France
Abstract : In this paper, we study instances of complex neural networks, i.e. neural netwo rks with complex topologies. We use Self-Organizing Map neural networks whose n eighbourhood relationships are defined by a complex network, to classify handwr itten digits. We show that topology has a small impact on performance and robus tness to neuron failures, at least at long learning times. Performance may howe ver be increased (by almost $10\%$) by artificial evolution of the network topo logy. In our experimental conditions, the evolved networks are more random than their parents, but display a more heterogeneous degree distribution.
Type de document :
Communication dans un congrès
Jürgen Jost. ECCS'07, Oct 2007, Dresden, Germany. 2007
Liste complète des métadonnées

https://hal.inria.fr/inria-00175721
Contributeur : Marc Schoenauer <>
Soumis le : lundi 1 octobre 2007 - 08:45:14
Dernière modification le : jeudi 10 mai 2018 - 02:06:58
Document(s) archivé(s) le : vendredi 9 avril 2010 - 16:47:03

Fichiers

EVVON_v2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00175721, version 1
  • ARXIV : 0710.0213

Collections

Citation

Fei Jiang, Hugues Berry, Marc Schoenauer. Optimising the topology of complex neural networks. Jürgen Jost. ECCS'07, Oct 2007, Dresden, Germany. 2007. 〈inria-00175721〉

Partager

Métriques

Consultations de la notice

384

Téléchargements de fichiers

738