Optimising the topology of complex neural networks
| dc.creator | Jiang, Fei | |
| dc.creator | Berry, Hugues | |
| dc.creator | Schoenauer, Marc | |
| dc.date | 2007-10-01 | |
| dc.date.accessioned | 2026-07-07T08:33:15Z | |
| dc.date.available | 2026-07-07T08:33:15Z | |
| dc.description | 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. | |
| dc.identifier | https://arxiv.org/abs/0710.0213 | |
| dc.identifier | http://arxiv.org/abs/0710.0213 | |
| dc.identifier | Dans ECCS'07 (2007) | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/139061 | |
| dc.subject | Neural and Evolutionary Computing | |
| dc.subject | Artificial Intelligence | |
| dc.title | Optimising the topology of complex neural networks | |
| dc.type | text |