Optimising the topology of complex neural networks

dc.creatorJiang, Fei
dc.creatorBerry, Hugues
dc.creatorSchoenauer, Marc
dc.date2007-10-01
dc.date.accessioned2026-07-07T08:33:15Z
dc.date.available2026-07-07T08:33:15Z
dc.descriptionIn 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.
dc.identifierhttps://arxiv.org/abs/0710.0213
dc.identifierhttp://arxiv.org/abs/0710.0213
dc.identifierDans ECCS'07 (2007)
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/139061
dc.subjectNeural and Evolutionary Computing
dc.subjectArtificial Intelligence
dc.titleOptimising the topology of complex neural networks
dc.typetext

Files

Collections