Show simple item record

dc.contributor.authorCastro Peña, Juan Luis
dc.contributor.authorTrillas i Gay, Enric
dc.date.accessioned2007-09-18T12:58:30Z
dc.date.available2007-09-18T12:58:30Z
dc.date.issued1998
dc.identifier.issn1134-5632
dc.identifier.urihttp://hdl.handle.net/2099/3501
dc.description.abstractThis paper establishes the equivalence between multilayer feedforward networks and linear combinations of Lukasiewicz propositions. In this sense, multilayer forward networks have a logic interpretation, which should permit to apply logical techniques in the neural networks framework.
dc.format.extent23-37
dc.language.isoeng
dc.publisherUniversitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica
dc.relation.ispartofMathware & soft computing . 1998 Vol. 5 Núm. 1
dc.rightsReconeixement-NoComercial-CompartirIgual 3.0 Espanya
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.otherFeedforward networks
dc.subject.otherLukasiewicz logic
dc.subject.otherUniversal aproximators
dc.subject.otherSquashing functions
dc.titleThe logic of neural networks
dc.typeArticle
dc.subject.lemacLògica matemàtica
dc.subject.lemacXarxes neuronals (Informàtica)
dc.subject.amsClassificació AMS::03 Mathematical logic and foundations::03B General logic
dc.rights.accessOpen Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain