Comitê de redes neurais quânticas
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da UFRPE |
Texto Completo: | http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/8675 |
Resumo: | Deep Neural Networks open several possibilities to solve hard problems. The advancement in the use of quantum computation has allowed us to use quantum features which have no classical counterpart. It has brought forth many algorithms and techniques in the field of quantum machine learning (QML). One of the proposals was a binary quantum neural network (QBNN) which used an amplification method based on the well-known Grover’s algorithm search. Besides the fact of being a purely quantum method, it used an architecture selection mechanism as a meaningful approach. Despite its enhancements, one of the main disadvantages is the consumption of a lot of quantum computational resources. Therefore, We present a series of improvements from loading the data using a superposition instead of an original base encoding. Further, we also change the training process, replacing the costly Grover’s search with gradient descent optimization. It reduces the quantum computational loss, shrinking the number of operations and qubits. Moreover, we applied the concept of ensemble classification, instead of using a single specific quantum binary weight. Finally we show that it is possible to achieve a general model better using the Grover algorithm. |
id |
URPE_9258c2698a780b7df3bd4c6e5be78f53 |
---|---|
oai_identifier_str |
oai:tede2:tede2/8675 |
network_acronym_str |
URPE |
network_name_str |
Biblioteca Digital de Teses e Dissertações da UFRPE |
repository_id_str |
|
spelling |
SILVA, Adenilton José dahttp://lattes.cnpq.br/5765619982001841LEAL, Daivid Vasconcelos2022-10-06T16:19:32Z2022-06-03LEAL, Daivid Vasconcelos. Comitê de redes neurais quânticas. 2022. 56 f. Dissertação (Programa de Pós-Graduação em Informática Aplicada) - Universidade Federal Rural de Pernambuco, Recife.http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/8675Deep Neural Networks open several possibilities to solve hard problems. The advancement in the use of quantum computation has allowed us to use quantum features which have no classical counterpart. It has brought forth many algorithms and techniques in the field of quantum machine learning (QML). One of the proposals was a binary quantum neural network (QBNN) which used an amplification method based on the well-known Grover’s algorithm search. Besides the fact of being a purely quantum method, it used an architecture selection mechanism as a meaningful approach. Despite its enhancements, one of the main disadvantages is the consumption of a lot of quantum computational resources. Therefore, We present a series of improvements from loading the data using a superposition instead of an original base encoding. Further, we also change the training process, replacing the costly Grover’s search with gradient descent optimization. It reduces the quantum computational loss, shrinking the number of operations and qubits. Moreover, we applied the concept of ensemble classification, instead of using a single specific quantum binary weight. Finally we show that it is possible to achieve a general model better using the Grover algorithm.Redes Neurais Profundas abrem várias possibilidades para resolver problemas difíceis. O avanço no uso da computação quântica nos permitiu usar recursos quânticos que não têm contrapartida clássica, e nos trouxe muitos algoritmos e técnicas no campo do aprendizado de máquina quântica (AMQ). Uma das propostas do ramo do AMQ era uma rede neural quântica binária (RNQB) que usa um método de amplificação baseado no conhecido algoritmo de busca de Grover. Além de ser um método puramente quântico, utilizou-se um mecanismo de seleção de arquitetura como uma abordagem significativa. Apesar dos aprimoramentos, uma das principais desvantagens é o consumo de muitos recursos computacionais quânticos, que não disponibilizamos nos dias atuais. Portanto, apresentamos uma série de melhorias na proposta, desde carregar os dados usando uma sobreposição em vez de uma codificação de base original, até a utilização de menos Qubits e menos profundidade do circuito quântico proposto. Além disso, também mudamos o processo de treinamento, substituindo a custosa pesquisa de Grover por otimização de gradiente descendente, fazendo com que possamos treinar não somente uma RNBQ mas sim um Comitê de Classificadores dentro de um sistema Quântico, assim, diminuindo o número de operações no Computador Quântico. Finalmente, mostramos que é possível obter um modelo geral melhor do que utilizar o algoritmo de Grover.Submitted by Mario BC (mario@bc.ufrpe.br) on 2022-10-06T16:19:32Z No. of bitstreams: 1 Daivid Vasconcelos Leal.pdf: 1156476 bytes, checksum: 60b295aabf3d078e95c9a138c17912a9 (MD5)Made available in DSpace on 2022-10-06T16:19:32Z (GMT). No. of bitstreams: 1 Daivid Vasconcelos Leal.pdf: 1156476 bytes, checksum: 60b295aabf3d078e95c9a138c17912a9 (MD5) Previous issue date: 2022-06-03application/pdfporUniversidade Federal Rural de PernambucoPrograma de Pós-Graduação em Informática AplicadaUFRPEBrasilDepartamento de Estatística e InformáticaComputação quânticaAprendizado de máquinaRede neural artificialCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOComitê de redes neurais quânticasinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis-8268485641417162699600600600-67745551403961205013671711205811204509info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UFRPEinstname:Universidade Federal Rural de Pernambuco (UFRPE)instacron:UFRPEORIGINALDaivid Vasconcelos Leal.pdfDaivid Vasconcelos Leal.pdfapplication/pdf1156476http://www.tede2.ufrpe.br:8080/tede2/bitstream/tede2/8675/2/Daivid+Vasconcelos+Leal.pdf60b295aabf3d078e95c9a138c17912a9MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82165http://www.tede2.ufrpe.br:8080/tede2/bitstream/tede2/8675/1/license.txtbd3efa91386c1718a7f26a329fdcb468MD51tede2/86752022-10-06 13:19:32.569oai:tede2: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Biblioteca Digital de Teses e Dissertaçõeshttp://www.tede2.ufrpe.br:8080/tede/PUBhttp://www.tede2.ufrpe.br:8080/oai/requestbdtd@ufrpe.br ||bdtd@ufrpe.bropendoar:2024-05-28T12:37:17.257468Biblioteca Digital de Teses e Dissertações da UFRPE - Universidade Federal Rural de Pernambuco (UFRPE)false |
dc.title.por.fl_str_mv |
Comitê de redes neurais quânticas |
title |
Comitê de redes neurais quânticas |
spellingShingle |
Comitê de redes neurais quânticas LEAL, Daivid Vasconcelos Computação quântica Aprendizado de máquina Rede neural artificial CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
title_short |
Comitê de redes neurais quânticas |
title_full |
Comitê de redes neurais quânticas |
title_fullStr |
Comitê de redes neurais quânticas |
title_full_unstemmed |
Comitê de redes neurais quânticas |
title_sort |
Comitê de redes neurais quânticas |
author |
LEAL, Daivid Vasconcelos |
author_facet |
LEAL, Daivid Vasconcelos |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
SILVA, Adenilton José da |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/5765619982001841 |
dc.contributor.author.fl_str_mv |
LEAL, Daivid Vasconcelos |
contributor_str_mv |
SILVA, Adenilton José da |
dc.subject.por.fl_str_mv |
Computação quântica Aprendizado de máquina Rede neural artificial |
topic |
Computação quântica Aprendizado de máquina Rede neural artificial CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
description |
Deep Neural Networks open several possibilities to solve hard problems. The advancement in the use of quantum computation has allowed us to use quantum features which have no classical counterpart. It has brought forth many algorithms and techniques in the field of quantum machine learning (QML). One of the proposals was a binary quantum neural network (QBNN) which used an amplification method based on the well-known Grover’s algorithm search. Besides the fact of being a purely quantum method, it used an architecture selection mechanism as a meaningful approach. Despite its enhancements, one of the main disadvantages is the consumption of a lot of quantum computational resources. Therefore, We present a series of improvements from loading the data using a superposition instead of an original base encoding. Further, we also change the training process, replacing the costly Grover’s search with gradient descent optimization. It reduces the quantum computational loss, shrinking the number of operations and qubits. Moreover, we applied the concept of ensemble classification, instead of using a single specific quantum binary weight. Finally we show that it is possible to achieve a general model better using the Grover algorithm. |
publishDate |
2022 |
dc.date.accessioned.fl_str_mv |
2022-10-06T16:19:32Z |
dc.date.issued.fl_str_mv |
2022-06-03 |
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.citation.fl_str_mv |
LEAL, Daivid Vasconcelos. Comitê de redes neurais quânticas. 2022. 56 f. Dissertação (Programa de Pós-Graduação em Informática Aplicada) - Universidade Federal Rural de Pernambuco, Recife. |
dc.identifier.uri.fl_str_mv |
http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/8675 |
identifier_str_mv |
LEAL, Daivid Vasconcelos. Comitê de redes neurais quânticas. 2022. 56 f. Dissertação (Programa de Pós-Graduação em Informática Aplicada) - Universidade Federal Rural de Pernambuco, Recife. |
url |
http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/8675 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.program.fl_str_mv |
-8268485641417162699 |
dc.relation.confidence.fl_str_mv |
600 600 600 |
dc.relation.department.fl_str_mv |
-6774555140396120501 |
dc.relation.cnpq.fl_str_mv |
3671711205811204509 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal Rural de Pernambuco |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Informática Aplicada |
dc.publisher.initials.fl_str_mv |
UFRPE |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Departamento de Estatística e Informática |
publisher.none.fl_str_mv |
Universidade Federal Rural de Pernambuco |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da UFRPE instname:Universidade Federal Rural de Pernambuco (UFRPE) instacron:UFRPE |
instname_str |
Universidade Federal Rural de Pernambuco (UFRPE) |
instacron_str |
UFRPE |
institution |
UFRPE |
reponame_str |
Biblioteca Digital de Teses e Dissertações da UFRPE |
collection |
Biblioteca Digital de Teses e Dissertações da UFRPE |
bitstream.url.fl_str_mv |
http://www.tede2.ufrpe.br:8080/tede2/bitstream/tede2/8675/2/Daivid+Vasconcelos+Leal.pdf http://www.tede2.ufrpe.br:8080/tede2/bitstream/tede2/8675/1/license.txt |
bitstream.checksum.fl_str_mv |
60b295aabf3d078e95c9a138c17912a9 bd3efa91386c1718a7f26a329fdcb468 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da UFRPE - Universidade Federal Rural de Pernambuco (UFRPE) |
repository.mail.fl_str_mv |
bdtd@ufrpe.br ||bdtd@ufrpe.br |
_version_ |
1810102266087079936 |