dc.contributor.author | Calcraft, L. | en_US |
dc.contributor.author | Adams, R.G. | en_US |
dc.contributor.author | Davey, N. | en_US |
dc.date.accessioned | 2007-10-01T09:55:51Z | |
dc.date.available | 2007-10-01T09:55:51Z | |
dc.date.issued | 2007 | en_US |
dc.identifier.citation | In: Procs of the 15th European Symposium on Artificial Neural Networks, ESANN2007 | en_US |
dc.identifier.other | 900844 | en_US |
dc.identifier.uri | http://hdl.handle.net/2299/764 | |
dc.description.abstract | Our work is concerned with finding optimum connection strategies in high-performance associative memory models. Taking inspiration from axonal branching in biological neurons, we impose a displacement of the point of efferent arborisation, so that the output from each node travels a certain distance before branching to connect to other units. This technique is applied to networks constructed with a connectivity profile based on Gaussian distributions, and the results compared to those obtained with a network containing purely local connections, displaced in the same manner. It is found that displacement of the point of arborisation has a very beneficial effect on the performance of both network types, with the displaced locally-connected network performing the best. | en |
dc.format.extent | 387796 bytes | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.title | Sparsely-connected associative memory models with displaced connectivity. | en_US |
dc.type | Conference paper | en_US |
herts.preservation.rarelyaccessed | true | |