Mostrar el registro sencillo del ítem

dc.contributor.author
Rubiolo, María Florencia  
dc.contributor.author
Stegmayer, Georgina  
dc.contributor.author
Milone, Diego Humberto  
dc.date.available
2017-03-31T14:08:47Z  
dc.date.issued
2013-07  
dc.identifier.citation
Rubiolo, María Florencia; Stegmayer, Georgina; Milone, Diego Humberto; Compressing arrays of classifiers using Volterra-Neural Network: application to face recognition; Springer; Neural Computing And Applications; 23; 6; 7-2013; 1687-1701  
dc.identifier.issn
0941-0643  
dc.identifier.uri
http://hdl.handle.net/11336/14571  
dc.description.abstract
Model compression is required when large models are used, for example, for a classification task, but there are transmission, space, time or computing constraints that have to be fulfilled. Multilayer Perceptron (MLP) models have been traditionally used as classifiers. Depending on the problem, they may need a large number of parameters (neuron functions, weights and bias) to obtain an acceptable performance. This work proposes a technique to compress an array of MLPs, through the weights of a Volterra-Neural Network (Volterra-NN), maintaining its classification performance. It will be shown that several MLP topologies can be well-compressed into the first, second and third order (Volterra-NN) outputs. The obtained results show that these outputs can be used to build an array of (Volterra-NN) that needs significantly less parameters than the original array of MLPs, furthermore having the same high accuracy. The Volterra-NN compression capabilities were tested for solving a face recognition problem. Experimental results are presented on two well-known face databases: ORL and FERET.  
dc.format
application/pdf  
dc.language.iso
eng  
dc.publisher
Springer  
dc.rights
info:eu-repo/semantics/openAccess  
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/  
dc.subject
Model Compression  
dc.subject
Array of Neural Networks  
dc.subject
Volterra-Neural Network  
dc.subject
Face Recognition  
dc.subject.classification
Ciencias de la Información y Bioinformática  
dc.subject.classification
Ciencias de la Computación e Información  
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS  
dc.title
Compressing arrays of classifiers using Volterra-Neural Network: application to face recognition  
dc.type
info:eu-repo/semantics/article  
dc.type
info:ar-repo/semantics/artículo  
dc.type
info:eu-repo/semantics/publishedVersion  
dc.date.updated
2017-03-22T15:19:28Z  
dc.journal.volume
23  
dc.journal.number
6  
dc.journal.pagination
1687-1701  
dc.journal.pais
Alemania  
dc.journal.ciudad
Berlin  
dc.description.fil
Fil: Rubiolo, María Florencia. Universidad Tecnologica Nacional. Facultad Regional Santa Fe. Centro de Investigacion y Desarrollo de Ingenieria en Sistemas de Informacion; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Santa Fe; Argentina  
dc.description.fil
Fil: Stegmayer, Georgina. Universidad Tecnologica Nacional. Facultad Regional Santa Fe. Centro de Investigacion y Desarrollo de Ingenieria en Sistemas de Informacion; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Santa Fe; Argentina  
dc.description.fil
Fil: Milone, Diego Humberto. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Centro Cientifico Tecnológico Santa Fe. Instituto de Investigacion en Señales, Sistemas e Inteligencia Computacional; Argentina; Argentina  
dc.journal.title
Neural Computing And Applications  
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/http://link.springer.com/article/10.1007/s00521-012-1129-5  
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1007/s00521-012-1129-5