Optimising the topology of complex neural networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Optimising the topology of complex neural networks


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.
Fichier principal
Vignette du fichier
EVVON_v2.pdf (159.52 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00175721 , version 1 (01-10-2007)


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


Fei Jiang, Hugues Berry, Marc Schoenauer. Optimising the topology of complex neural networks. ECCS'07, Complex Systesms Society, Oct 2007, Dresden, Germany. ⟨inria-00175721⟩
176 View
130 Download



Gmail Facebook X LinkedIn More