The impact of network topology on self-organizing maps - Laboratoire de recherche en informatique. Équipe: Apprentissage et optimisation Access content directly
Conference Papers Year : 2009

The impact of network topology on self-organizing maps

Abstract

In this paper, we study instances of complex neural networks, i.e. neural networks with complex topologies. We use Self-Organizing Map neural networks whose neighborhood relationships are defined by a complex network, to classify handwritten digits. We show that topology has a small impact on performance and robustness to neuron failures, at least at long learning times. Performance may however be increased (by almost 10%) by evolutionary optimization of the network topology. In our experimental conditions, the evolved networks are more random than their parents, but display a more heterogeneous degree distribution.
Fichier principal
Vignette du fichier
jiang2009.pdf (505.37 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

inria-00633584 , version 1 (27-03-2024)

Licence

Identifiers

  • HAL Id : inria-00633584 , version 1

Cite

Fei Jiang, Hugues Berry, Marc Schoenauer. The impact of network topology on self-organizing maps. First ACM/SIGEVO Summit on Genetic and Evolutionary Computation, GEC-2009, Jun 2009, Shangai, China. ⟨inria-00633584⟩
281 View
6 Download

Share

Gmail Mastodon Facebook X LinkedIn More