A neural network with competitive layers for character recognition

A structure and functioning mechanisms of a neural network with competitive layers are described. The network is intended to solve the character recognition task. The network consists of several competitive layers of neurons. Each layer is a neural network consisting of a number of neurons represent...

Descripción completa

Detalles Bibliográficos
Autores: Goltsev, Alexander|||0000-0002-2961-0908, Gritsenko, Vladimir
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:263044
Acceso en línea:https://ddd.uab.cat/record/263044
https://dx.doi.org/urn:doi:10.5565/rev/elcvia.1392
Access Level:acceso abierto
Palabra clave:Pattern recognition
Learning
Classification
Character and text recognition
Handwriting recognition
Neural networks
Character recognition
Machine learning
id ES_44ab69fc2e266b58de01e10884e4e6d5
oai_identifier_str oai:ddd.uab.cat:263044
network_acronym_str ES
network_name_str España
repository_id_str
spelling A neural network with competitive layers for character recognitionGoltsev, Alexander|||0000-0002-2961-0908Gritsenko, VladimirPattern recognitionLearningClassificationCharacter and text recognitionHandwriting recognitionNeural networksCharacter recognitionMachine learningA structure and functioning mechanisms of a neural network with competitive layers are described. The network is intended to solve the character recognition task. The network consists of several competitive layers of neurons. Each layer is a neural network consisting of a number of neurons represented as a layer. The number of neural layers is equal to the number of recognized classes. All neural layers have one-to-one correspondence with one another and with the input raster. The neurons of every layer have mutual lateral learning connections, which weights are modified during the learning process. There is a competitive (inhibitory) relationship between all neural layers. This competitive interaction is realized by means of a "winner-take-all" (WTA) procedure which aim is to select the layer with the highest level of neural activity. Validation of the network has been done in experiments on recognition of handwritten digits of the MNIST database. The experiments have demonstrated that its error rate is few less than 2%, which is not a high result, but it is compensated by rather fast data processing and a very simple structure and functioning mechanisms. 22022-01-0120222022-01-01Articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://ddd.uab.cat/record/263044https://dx.doi.org/urn:doi:10.5565/rev/elcvia.1392reponame:Dipòsit Digital de Documents de la UABinstname:Universitat Autònoma de BarcelonaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.https://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ddd.uab.cat:2630442026-06-06T12:50:31Z
dc.title.none.fl_str_mv A neural network with competitive layers for character recognition
title A neural network with competitive layers for character recognition
spellingShingle A neural network with competitive layers for character recognition
Goltsev, Alexander|||0000-0002-2961-0908
Pattern recognition
Learning
Classification
Character and text recognition
Handwriting recognition
Neural networks
Character recognition
Machine learning
title_short A neural network with competitive layers for character recognition
title_full A neural network with competitive layers for character recognition
title_fullStr A neural network with competitive layers for character recognition
title_full_unstemmed A neural network with competitive layers for character recognition
title_sort A neural network with competitive layers for character recognition
dc.creator.none.fl_str_mv Goltsev, Alexander|||0000-0002-2961-0908
Gritsenko, Vladimir
author Goltsev, Alexander|||0000-0002-2961-0908
author_facet Goltsev, Alexander|||0000-0002-2961-0908
Gritsenko, Vladimir
author_role author
author2 Gritsenko, Vladimir
author2_role author
dc.subject.none.fl_str_mv Pattern recognition
Learning
Classification
Character and text recognition
Handwriting recognition
Neural networks
Character recognition
Machine learning
topic Pattern recognition
Learning
Classification
Character and text recognition
Handwriting recognition
Neural networks
Character recognition
Machine learning
description A structure and functioning mechanisms of a neural network with competitive layers are described. The network is intended to solve the character recognition task. The network consists of several competitive layers of neurons. Each layer is a neural network consisting of a number of neurons represented as a layer. The number of neural layers is equal to the number of recognized classes. All neural layers have one-to-one correspondence with one another and with the input raster. The neurons of every layer have mutual lateral learning connections, which weights are modified during the learning process. There is a competitive (inhibitory) relationship between all neural layers. This competitive interaction is realized by means of a "winner-take-all" (WTA) procedure which aim is to select the layer with the highest level of neural activity. Validation of the network has been done in experiments on recognition of handwritten digits of the MNIST database. The experiments have demonstrated that its error rate is few less than 2%, which is not a high result, but it is compensated by rather fast data processing and a very simple structure and functioning mechanisms.
publishDate 2022
dc.date.none.fl_str_mv 2
2022-01-01
2022
2022-01-01
dc.type.none.fl_str_mv Article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://ddd.uab.cat/record/263044
https://dx.doi.org/urn:doi:10.5565/rev/elcvia.1392
url https://ddd.uab.cat/record/263044
https://dx.doi.org/urn:doi:10.5565/rev/elcvia.1392
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Dipòsit Digital de Documents de la UAB
instname:Universitat Autònoma de Barcelona
instname_str Universitat Autònoma de Barcelona
reponame_str Dipòsit Digital de Documents de la UAB
collection Dipòsit Digital de Documents de la UAB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407109483855872
score 15,300719

Similares en LA Referencia