Show simple item record

dc.contributor.authorCreatore, Celestino
dc.contributor.authorSabathiel, Silvester
dc.contributor.authorSolstad, Trygve
dc.date.accessioned2022-09-16T12:13:20Z
dc.date.available2022-09-16T12:13:20Z
dc.date.created2021-07-01T12:26:30Z
dc.date.issued2021
dc.identifier.issn0010-0277
dc.identifier.urihttps://hdl.handle.net/11250/3018480
dc.description.abstractA system for approximate number discrimination has been shown to arise in at least two types of hierarchical neural network models—a generative Deep Belief Network (DBN) and a Hierarchical Convolutional Neural Network (HCNN) trained to classify natural objects. Here, we investigate whether the same two network architectures can learn to recognise exact numerosity. A clear difference in performance could be traced to the specificity of the unit responses that emerged in the last hidden layer of each network. In the DBN, the emergence of a layer of monotonic ‘summation units’ was sufficient to produce classification behaviour consistent with the behavioural signature of the approximate number system. In the HCNN, a layer of units uniquely tuned to the transition between particular numerosities effectively encoded a thermometer-like ‘numerosity code’ that ensured near-perfect classification accuracy. The results support the notion that parallel pattern-recognition mechanisms may give rise to exact and approximate number concepts, both of which may contribute to the learning of symbolic numbers and arithmetic.en_US
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.titleLearning exact enumeration and approximate estimation in deep neural network modelsen_US
dc.typeJournal articleen_US
dc.typePeer revieweden_US
dc.description.versionpublishedVersionen_US
dc.source.volume215en_US
dc.source.journalCognitionen_US
dc.identifier.doi10.1016/j.cognition.2021.104815
dc.identifier.cristin1919823
dc.relation.projectNorges forskningsråd: 283441en_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode2


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal