Publication:
From continous behaviour to discrete knowledge

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)es
dc.contributor.authorLedezma Espino, Agapito Ismael
dc.contributor.authorFernández, Fernando
dc.contributor.authorAler, Ricardo
dc.date.accessioned2009-12-14T13:41:59Z
dc.date.available2009-12-14T13:41:59Z
dc.date.issued2009
dc.descriptionProceeding of: 7th InternationalWork-Conference on Artificial and Natural Neural Networks, IWANN 2003, Maó, Menorca, Spain, June 3-6, 2003, Proceedings, Part II
dc.description.abstractNeural networks have proven to be very powerful techniques for solving a wide range of tasks. However, the learned concepts are unreadable for humans. Some works try to obtain symbolic models from the networks, once these networks have been trained, allowing to understand the model by means of decision trees or rules that are closer to human understanding. The main problem of this approach is that neural networks output a continuous range of values, so even though a symbolic technique could be used to work with continuous classes, this output would still be hard to understand for humans. In this work, we present a system that is able to model a neural network behaviour by discretizing its outputs with a vector quantization approach, allowing to apply the symbolic method.
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationArtificial neural nets problem solving methods, Springer, 2009, p. 217-224
dc.identifier.doi10.1007/3-540-44869-1_28
dc.identifier.isbn978-3-540-40211-4
dc.identifier.issn0302-9743 (Print)
dc.identifier.issn1611-3349 (Online)
dc.identifier.publicationfirstpage217
dc.identifier.publicationlastpage224
dc.identifier.publicationtitleArtificial neural nets problem solving methods
dc.identifier.urihttps://hdl.handle.net/10016/6035
dc.language.isoeng
dc.publisherSpringer
dc.relation.eventdateJune 3-6, 2003
dc.relation.eventnumber7
dc.relation.eventplaceMaó (Menorca, Spain)
dc.relation.eventtitleInternationalWork-Conference on Artificial and Natural Neural Networks, IWANN
dc.relation.ispartofseriesLecture notes in computer science, vol. 2687
dc.relation.publisherversionhttp://dx.doi.org/10.1007/3-540-44869-1_28
dc.rights.accessRightsopen access
dc.rights.uri© Springer
dc.subject.otherNeural networks
dc.titleFrom continous behaviour to discrete knowledge
dc.typeconference paper*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
from_aler_LNCS_2003_ps.pdf
Size:
576.94 KB
Format:
Adobe Portable Document Format
Download
Collections
DI - GCERN - Capítulos de Monografías
DI - GCERN - Comunicaciones en Congresos y otros eventos