q-Gaussians for pattern recognition
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFPE |
Texto Completo: | https://repositorio.ufpe.br/handle/123456789/17361 |
Resumo: | Pattern recognition plays an important role for solving many problems in our everyday lives: from simple tasks such as reading texts to more complex ones like driving cars. Subconsciously, the recognition of patterns is instantaneous and an innate ability to every human. However, programming (or “teaching”) a machine how to do the same can present an incredibly difficult task. There are many situations where irrelevant or misleading patterns, poorly represented classes, and complex decision boundaries make recognition very hard, or even impossible by current standards. Important contributions to the field of pattern recognition have been attained through the adoption of methods of statistical mechanics, which has paved the road for much of the research done in academia and industry, ranging from the revival of connectionism to modern day deep learning. Yet traditional statistical mechanics is not universal and has a limited domain of applicability - outside this domain it can make wrong predictions. Non-extensive statistical mechanics has recently emerged to cover a variety of anomalous situations that cannot be described within standard Boltzmann-Gibbs theory, such as non-ergodic systems characterized by long-range interactions, or long-term memories. The literature on pattern recognition is vast, and scattered with applications of non-extensive statistical mechanics. However, most of this work has been done using non-extensive entropy, and little can be found on practical applications of other non-extensive constructs. In particular, non-extensive entropy is widely used to improve segmentation of images that possess strongly correlated patterns, while only a small number of works employ concepts other than entropy for solving similar recognition tasks. The main goal of this dissertation is to expand applications of non-extensive distributions, namely the q-Gaussian, in pattern recognition. We present ourcontributions in the form of two (published) articles where practical uses of q-Gaussians are explored in neural networks. The first paper introduces q Gaussian transfer functions to improve classification of random neural networks, and the second paper extends this work to ensembles which involves combining a set of such classifiers via majority voting. |
id |
UFPE_6b6cee3e7741cd929bcf5a5872400aa0 |
---|---|
oai_identifier_str |
oai:repositorio.ufpe.br:123456789/17361 |
network_acronym_str |
UFPE |
network_name_str |
Repositório Institucional da UFPE |
repository_id_str |
2221 |
spelling |
STOSIC, DusanLUDERMIR, Teresa Bernarda2016-07-13T19:23:52Z2016-07-13T19:23:52Z2016-03-01https://repositorio.ufpe.br/handle/123456789/17361Pattern recognition plays an important role for solving many problems in our everyday lives: from simple tasks such as reading texts to more complex ones like driving cars. Subconsciously, the recognition of patterns is instantaneous and an innate ability to every human. However, programming (or “teaching”) a machine how to do the same can present an incredibly difficult task. There are many situations where irrelevant or misleading patterns, poorly represented classes, and complex decision boundaries make recognition very hard, or even impossible by current standards. Important contributions to the field of pattern recognition have been attained through the adoption of methods of statistical mechanics, which has paved the road for much of the research done in academia and industry, ranging from the revival of connectionism to modern day deep learning. Yet traditional statistical mechanics is not universal and has a limited domain of applicability - outside this domain it can make wrong predictions. Non-extensive statistical mechanics has recently emerged to cover a variety of anomalous situations that cannot be described within standard Boltzmann-Gibbs theory, such as non-ergodic systems characterized by long-range interactions, or long-term memories. The literature on pattern recognition is vast, and scattered with applications of non-extensive statistical mechanics. However, most of this work has been done using non-extensive entropy, and little can be found on practical applications of other non-extensive constructs. In particular, non-extensive entropy is widely used to improve segmentation of images that possess strongly correlated patterns, while only a small number of works employ concepts other than entropy for solving similar recognition tasks. The main goal of this dissertation is to expand applications of non-extensive distributions, namely the q-Gaussian, in pattern recognition. We present ourcontributions in the form of two (published) articles where practical uses of q-Gaussians are explored in neural networks. The first paper introduces q Gaussian transfer functions to improve classification of random neural networks, and the second paper extends this work to ensembles which involves combining a set of such classifiers via majority voting.CAPESReconhecimento de padrões tem um papel importante na solução de diversos problemas no nosso quotidiano: a partir de tarefas simples como ler textos, até as mais complexas como dirigir carros. Inconscientemente, o reconhecimento de padrões pelo cérebro é instantâneo, representando uma habilidade inata de cada ser humano. No entanto, programar (ou “ensinar”) uma máquina para fazer o mesmo pode se tornar uma tarefa extremamente difícil. Há muitas situações onde padrões irrelevantes ou enganosos, classes mal representadas, ou bordas de decisões complexas, tornam o reconhecimento muito difícil, ou mesmo impossível pelos padrões atuais. Diversas contribuições importantes na área de reconhecimento de padrões foram alcançadas através da aplicação de métodos provenientes da mecânica estatística, que estimularam uma grande parte da pesquisa conduzida na academia bem como na indústria, desde o renascimento de conexionismo até o moderno conceito de “deep learning”. No entanto, a mecânica estatística tradicional não é universal e tem um domínio de aplicação limitado - fora deste domínio ela pode fazer previsões erradas. A mecânica estatística não-extensiva surgiu recentemente para atender uma variedade de situações anômalas que não podem ser descritas de forma adequada com a teoria de Boltzmann-Gibbs, tais como sistemas não-ergódicos, caracterizadas por interações de longo alcance, ou memórias de longo prazo. A literatura sobre reconhecimento de padrões é vasta, e dispersa com aplicações da mecânica estatística não-extensiva. No entanto, a maioria destes trabalhos utilizam a entropia não-extensiva, e existem poucas aplicações práticas de outros conceitos não-extensivos. Em particular, a entropia não extensiva é amplamente usada para aperfeiçoar segmentação de imagens que possuem padrões fortemente correlacionados, enquanto apenas um pequeno número de trabalhos empregam outros conceitos não-extensivos para resolver tarefas semelhantes. O objetivo principal desta dissertação é expandir aplicações de distribuições não-extensivas, como a q-Gaussiana, em reconhecimento de padrões. Nos apresentamos as nossas contribuições no formato de dois artigos (publicados) onde exploramos usos práticos da q-Gaussiana em redes neurais. O primeiro artigo introduz funções de transferência baseados na q-Gaussiana para aperfeiçoar a classificação de redes neurais aleatórias, e o segundo artigo estende este trabalho para ensembles, onde um conjunto de tais classificadores são combinados através de votação por maioria.engUniversidade Federal de PernambucoPrograma de Pos Graduacao em Ciencia da ComputacaoUFPEBrasilAttribution-NonCommercial-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessInteligência artificialReconhecimento de padrõesRedes neurais.q-Gaussians for pattern recognitioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesismestradoreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPETHUMBNAILDusan Stosic - dissertacao de mestrado.pdf.jpgDusan Stosic - dissertacao de mestrado.pdf.jpgGenerated Thumbnailimage/jpeg1239https://repositorio.ufpe.br/bitstream/123456789/17361/5/Dusan%20Stosic%20-%20dissertacao%20de%20mestrado.pdf.jpgc6b86ffa3fcf3dd8d519c1c3efcfe532MD55ORIGINALDusan Stosic - dissertacao de mestrado.pdfDusan Stosic - dissertacao de mestrado.pdfapplication/pdf6434406https://repositorio.ufpe.br/bitstream/123456789/17361/1/Dusan%20Stosic%20-%20dissertacao%20de%20mestrado.pdfdb312999879f1c3ebb1795ce764a272eMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-81232https://repositorio.ufpe.br/bitstream/123456789/17361/2/license_rdf66e71c371cc565284e70f40736c94386MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82311https://repositorio.ufpe.br/bitstream/123456789/17361/3/license.txt4b8a02c7f2818eaf00dcf2260dd5eb08MD53TEXTDusan Stosic - dissertacao de mestrado.pdf.txtDusan Stosic - dissertacao de mestrado.pdf.txtExtracted texttext/plain202020https://repositorio.ufpe.br/bitstream/123456789/17361/4/Dusan%20Stosic%20-%20dissertacao%20de%20mestrado.pdf.txtfd7a7fc538305c4544bfdb1d4fa94350MD54123456789/173612019-10-25 10:04:31.695oai:repositorio.ufpe.br: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Repositório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212019-10-25T13:04:31Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false |
dc.title.pt_BR.fl_str_mv |
q-Gaussians for pattern recognition |
title |
q-Gaussians for pattern recognition |
spellingShingle |
q-Gaussians for pattern recognition STOSIC, Dusan Inteligência artificial Reconhecimento de padrões Redes neurais. |
title_short |
q-Gaussians for pattern recognition |
title_full |
q-Gaussians for pattern recognition |
title_fullStr |
q-Gaussians for pattern recognition |
title_full_unstemmed |
q-Gaussians for pattern recognition |
title_sort |
q-Gaussians for pattern recognition |
author |
STOSIC, Dusan |
author_facet |
STOSIC, Dusan |
author_role |
author |
dc.contributor.author.fl_str_mv |
STOSIC, Dusan |
dc.contributor.advisor1.fl_str_mv |
LUDERMIR, Teresa Bernarda |
contributor_str_mv |
LUDERMIR, Teresa Bernarda |
dc.subject.por.fl_str_mv |
Inteligência artificial Reconhecimento de padrões Redes neurais. |
topic |
Inteligência artificial Reconhecimento de padrões Redes neurais. |
description |
Pattern recognition plays an important role for solving many problems in our everyday lives: from simple tasks such as reading texts to more complex ones like driving cars. Subconsciously, the recognition of patterns is instantaneous and an innate ability to every human. However, programming (or “teaching”) a machine how to do the same can present an incredibly difficult task. There are many situations where irrelevant or misleading patterns, poorly represented classes, and complex decision boundaries make recognition very hard, or even impossible by current standards. Important contributions to the field of pattern recognition have been attained through the adoption of methods of statistical mechanics, which has paved the road for much of the research done in academia and industry, ranging from the revival of connectionism to modern day deep learning. Yet traditional statistical mechanics is not universal and has a limited domain of applicability - outside this domain it can make wrong predictions. Non-extensive statistical mechanics has recently emerged to cover a variety of anomalous situations that cannot be described within standard Boltzmann-Gibbs theory, such as non-ergodic systems characterized by long-range interactions, or long-term memories. The literature on pattern recognition is vast, and scattered with applications of non-extensive statistical mechanics. However, most of this work has been done using non-extensive entropy, and little can be found on practical applications of other non-extensive constructs. In particular, non-extensive entropy is widely used to improve segmentation of images that possess strongly correlated patterns, while only a small number of works employ concepts other than entropy for solving similar recognition tasks. The main goal of this dissertation is to expand applications of non-extensive distributions, namely the q-Gaussian, in pattern recognition. We present ourcontributions in the form of two (published) articles where practical uses of q-Gaussians are explored in neural networks. The first paper introduces q Gaussian transfer functions to improve classification of random neural networks, and the second paper extends this work to ensembles which involves combining a set of such classifiers via majority voting. |
publishDate |
2016 |
dc.date.accessioned.fl_str_mv |
2016-07-13T19:23:52Z |
dc.date.available.fl_str_mv |
2016-07-13T19:23:52Z |
dc.date.issued.fl_str_mv |
2016-03-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpe.br/handle/123456789/17361 |
url |
https://repositorio.ufpe.br/handle/123456789/17361 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.publisher.program.fl_str_mv |
Programa de Pos Graduacao em Ciencia da Computacao |
dc.publisher.initials.fl_str_mv |
UFPE |
dc.publisher.country.fl_str_mv |
Brasil |
publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFPE instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Repositório Institucional da UFPE |
collection |
Repositório Institucional da UFPE |
bitstream.url.fl_str_mv |
https://repositorio.ufpe.br/bitstream/123456789/17361/5/Dusan%20Stosic%20-%20dissertacao%20de%20mestrado.pdf.jpg https://repositorio.ufpe.br/bitstream/123456789/17361/1/Dusan%20Stosic%20-%20dissertacao%20de%20mestrado.pdf https://repositorio.ufpe.br/bitstream/123456789/17361/2/license_rdf https://repositorio.ufpe.br/bitstream/123456789/17361/3/license.txt https://repositorio.ufpe.br/bitstream/123456789/17361/4/Dusan%20Stosic%20-%20dissertacao%20de%20mestrado.pdf.txt |
bitstream.checksum.fl_str_mv |
c6b86ffa3fcf3dd8d519c1c3efcfe532 db312999879f1c3ebb1795ce764a272e 66e71c371cc565284e70f40736c94386 4b8a02c7f2818eaf00dcf2260dd5eb08 fd7a7fc538305c4544bfdb1d4fa94350 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
attena@ufpe.br |
_version_ |
1802310829517832192 |