Combining Hebbian and reinforcement learning in a minibrain model

Simple item page
dc.creatorBosman, R. J. C.
dc.creatorvan Leeuwen, W. A.
dc.creatorWemmenhove, B.
dc.date2003-01-31
dc.date.accessioned2026-07-07T02:49:28Z
dc.date.available2026-07-07T02:49:28Z
dc.descriptionA toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of `path interference', which makes that the neural net quickly forgets previously learned input-output relations is tackled by adding a Hebbian term (proportional to the learning rate $η$) to the reinforcement term (proportional to $ρ$) in the learning rule. It is shown that the number of learning steps is reduced considerably if $1/4 < η/ρ< 1/2$, i.e., if the Hebbian term is neither too small nor too large compared to the reinforcement term.
dc.identifierhttps://arxiv.org/abs/cond-mat/0301627
dc.identifierhttp://arxiv.org/abs/cond-mat/0301627
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/20805
dc.subjectDisordered Systems and Neural Networks
dc.subjectQuantitative Biology
dc.titleCombining Hebbian and reinforcement learning in a minibrain model
dc.typetext

Files

Collections

arXiv