An Evolutionary Approach to Associative Memory in Recurrent Neural Networks

Simple item page
dc.creatorFujita, Sh.
dc.creatorNishimura, H.
dc.date1994-11-30
dc.date.accessioned2026-07-07T09:05:30Z
dc.date.available2026-07-07T09:05:30Z
dc.descriptionIn this paper, we investigate the associative memory in recurrent neural networks, based on the model of evolving neural networks proposed by Nolfi, Miglino and Parisi. Experimentally developed network has highly asymmetric synaptic weights and dilute connections, quite different from those of the Hopfield model. Some results on the effect of learning efficiency on the evolution are also presented.
dc.description7 pages, compressed and uuencoded postscript file
dc.identifierhttps://arxiv.org/abs/adap-org/9411003
dc.identifierhttp://arxiv.org/abs/adap-org/9411003
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/149699
dc.subjectAdaptation and Self-Organizing Systems
dc.subjectQuantitative Biology
dc.titleAn Evolutionary Approach to Associative Memory in Recurrent Neural Networks
dc.typetext

Files

Collections

arXiv