Regulation of specialists and generalists by neural variability improves pattern recognition performance

Biblos-e Archivo/Manakin Repository

Show simple item record

dc.contributor.author Montero, Aarón
dc.contributor.author Huerta, Ramón
dc.contributor.author Rodríguez, Francisco de Borja
dc.contributor.other UAM. Departamento de Ingeniería Informática es_ES
dc.date.accessioned 2016-10-14T14:21:35Z
dc.date.available 2016-10-14T14:21:35Z
dc.date.issued 2015-03-03
dc.identifier.citation Neurocomputing 151.P1 (2015): 69-77 en_US
dc.identifier.issn 0925-2312
dc.identifier.uri http://hdl.handle.net/10486/674181
dc.description This 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.2014.09.073 en_US
dc.description.abstract To 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.sponsorship This 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.extent 10 pag. es_ES
dc.format.mimetype application/pdf en
dc.language.iso eng en
dc.publisher Elsevier Inc. en_US
dc.relation.ispartof Neurocomputing en_US
dc.rights © 2015 Elsevier B.V. All rights reserved en_US
dc.subject.other Artificial neural networks en_US
dc.subject.other Neural threshold en_US
dc.subject.other Neural variability en_US
dc.subject.other Heterogeneity en_US
dc.subject.other Homogeneity en_US
dc.subject.other Olfactory system en_US
dc.subject.other Pattern recognition en_US
dc.subject.other Generalist neuron en_US
dc.subject.other Specialist neuron en_US
dc.subject.other Odor learning en_US
dc.subject.other Odor classification en_US
dc.subject.other Odor discrimination en_US
dc.subject.other Gain control en_US
dc.subject.other Unsupervised learning en_US
dc.subject.other Neural sparseness condition en_US
dc.title Regulation of specialists and generalists by neural variability improves pattern recognition performance en_US
dc.type article en_US
dc.subject.eciencia Informática es_ES
dc.date.embargoend 2017-03-03
dc.relation.publisherversion http://dx.doi.org/10.1016/j.neucom.2014.09.073
dc.identifier.doi 10.1016/j.neucom.2014.09.073
dc.identifier.publicationfirstpage 69
dc.identifier.publicationissue P1
dc.identifier.publicationlastpage 77
dc.identifier.publicationvolume 151
dc.relation.projectID Gobierno de España. TIN2010-19607 es_ES
dc.type.version info:eu-repo/semantics/acceptedVersion en
dc.contributor.group Neurocomputación Biológica (ING EPS-005) es_ES
dc.rights.cc Reconocimiento – NoComercial – SinObraDerivada es_ES
dc.rights.accessRights openAccess en
dc.authorUAM Huerta Rico, Ramón (259903)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record