The logic of neural networks

Castro Peña, Juan Luis; Trillas i Gay, Enric

dc.contributor.author	Castro Peña, Juan Luis
dc.contributor.author	Trillas i Gay, Enric
dc.date.accessioned	2007-09-18T12:58:30Z
dc.date.available	2007-09-18T12:58:30Z
dc.date.issued	1998
dc.identifier.issn	1134-5632
dc.identifier.uri	http://hdl.handle.net/2099/3501
dc.description.abstract	This 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.extent	23-37
dc.language.iso	eng
dc.publisher	Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica
dc.relation.ispartof	Mathware & soft computing . 1998 Vol. 5 Núm. 1
dc.rights	Reconeixement-NoComercial-CompartirIgual 3.0 Espanya
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.other	Feedforward networks
dc.subject.other	Lukasiewicz logic
dc.subject.other	Universal aproximators
dc.subject.other	Squashing functions
dc.title	The logic of neural networks
dc.type	Article
dc.subject.lemac	Lògica matemàtica
dc.subject.lemac	Xarxes neuronals (Informàtica)
dc.subject.ams	Classificació AMS::03 Mathematical logic and foundations::03B General logic
dc.rights.access	Open Access