Show simple item record

dc.contributor.authorMontero, Aarón
dc.contributor.authorHuerta, Ramón
dc.contributor.authorRodríguez Ortiz, Francisco Borja 
dc.contributor.otherUAM. Departamento de Ingeniería Informáticaes_ES
dc.date.accessioned2016-10-14T14:21:35Z
dc.date.available2016-10-14T14:21:35Z
dc.date.issued2015-03-03
dc.identifier.citationNeurocomputing 151.P1 (2015): 69-77en_US
dc.identifier.issn0925-2312
dc.identifier.urihttp://hdl.handle.net/10486/674181
dc.descriptionThis is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, VOL 151, Part 1, (2015), DOI 10.1016/j.neucom.2014.09.073en_US
dc.description.abstractTo analyze the impact of neural threshold variability in the mushroom body (MB) for pattern recognition, we used a computational model based on the olfactory system of insects. This model is a single-hidden-layer neural network (SLN) where the input layer represents the antennal lobe (AL). The remaining layers are in the MBs that are formed by the Kenyon cell (KC) layer and the output neurons that are responsible for odor learning. The binary code obtained for each odorant in the output layer by unsupervised learning was used to measure the classification error. This classification error allows us to identify the neural variability paradigm that achieves a better odor classification. The neural variability is provided by the neural threshold of activation. We compare two hypotheses: a unique threshold for all the neurons in the MB layer, which leads to no variability (homogeneity), and different thresholds for each MB layer (heterogeneity). The results show that, when there is threshold variability, odor classification performance improves. Neural variability induces populations of neurons that are specialists and generalists. Specialist neurons respond to fewer stimulus than the generalists. The proper combination of these two neuron types leads to performance improvement in the bioinspired classifier.en_US
dc.description.sponsorshipThis work was supported by the Spanish Government project TIN2010-19607 and predoctoral research grant BES-2011- 049274. R.H. acknowledges partial support by NIDCDR01DC011422- 01.en_US
dc.format.extent10 pag.es_ES
dc.format.mimetypeapplication/pdfen
dc.language.isoengen
dc.publisherElsevier Inc.en_US
dc.relation.ispartofNeurocomputingen_US
dc.rights© 2015 Elsevier B.V. All rights reserveden_US
dc.subject.otherArtificial neural networksen_US
dc.subject.otherNeural thresholden_US
dc.subject.otherNeural variabilityen_US
dc.subject.otherHeterogeneityen_US
dc.subject.otherHomogeneityen_US
dc.subject.otherOlfactory systemen_US
dc.subject.otherPattern recognitionen_US
dc.subject.otherGeneralist neuronen_US
dc.subject.otherSpecialist neuronen_US
dc.subject.otherOdor learningen_US
dc.subject.otherOdor classificationen_US
dc.subject.otherOdor discriminationen_US
dc.subject.otherGain controlen_US
dc.subject.otherUnsupervised learningen_US
dc.subject.otherNeural sparseness conditionen_US
dc.titleRegulation of specialists and generalists by neural variability improves pattern recognition performanceen_US
dc.typearticleen_US
dc.subject.ecienciaInformáticaes_ES
dc.date.embargoend2017-03-03
dc.relation.publisherversionhttp://dx.doi.org/10.1016/j.neucom.2014.09.073
dc.identifier.doi10.1016/j.neucom.2014.09.073
dc.identifier.publicationfirstpage69
dc.identifier.publicationissueP1
dc.identifier.publicationlastpage77
dc.identifier.publicationvolume151
dc.relation.projectIDGobierno de España. TIN2010-19607es_ES
dc.type.versioninfo:eu-repo/semantics/acceptedVersionen
dc.contributor.groupNeurocomputación Biológica (ING EPS-005)es_ES
dc.rights.ccReconocimiento – NoComercial – SinObraDerivadaes_ES
dc.rights.accessRightsopenAccessen
dc.authorUAMHuerta Rico, Ramón (259903)
dc.facultadUAMEscuela Politécnica Superior


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record