A quantum convolutional neural network for image classification

2021
book section
conference proceedings
13
cris.lastimport.wos2024-04-09T22:27:48Z
dc.abstract.enArtificial neural networks have achieved great success in many fields ranging from image recognition to video understanding. However, its high requirements for computing and memory resources have limited further development on processing big data with high dimensions. In recent years, advances in quantum computing show that building neural networks on quantum processors is a potential solution to this problem. In this paper, we propose a novel neural network model named Quantum Convolutional Neural Network (QCNN), aiming at utilizing the computing power of quantum systems to accelerate classical machine learning tasks. The designed QCNN is based on implementable quantum circuits and has a similar structure as classical convolutional neural networks. Numerical simulation results on the MNIST dataset demonstrate the effectiveness of our model.pl
dc.affiliationWydział Fizyki, Astronomii i Informatyki Stosowanej : Instytut Informatyki Stosowanejpl
dc.conference40th Chinese Control Conferencepl
dc.conference.citySzanghaj
dc.conference.countryChiny
dc.conference.datefinish2021-07-28
dc.conference.datestart2021-07-26
dc.contributor.authorLü, Yanxuanpl
dc.contributor.authorGao, Qingpl
dc.contributor.authorLü, Jinhupl
dc.contributor.authorOgorzałek, Maciej - 102456 pl
dc.contributor.authorZheng, Jinpl
dc.contributor.editorPeng, Chenpl
dc.contributor.editorSun, Jianpl
dc.date.accessioned2022-05-09T15:01:28Z
dc.date.available2022-05-09T15:01:28Z
dc.date.issued2021pl
dc.description.conftypeinternationalpl
dc.description.physical6329-6334pl
dc.description.seriesChinese Control Conference
dc.identifier.doi10.23919/CCC52363.2021.9550027pl
dc.identifier.eisbn978-9-8815-6380-4pl
dc.identifier.isbn978-1-6654-1195-0pl
dc.identifier.serieseissn2161-2927
dc.identifier.seriesissn1934-1768
dc.identifier.urihttps://ruj.uj.edu.pl/xmlui/handle/item/291834
dc.languageengpl
dc.language.containerengpl
dc.pubinfo[s.l.] : IEEEpl
dc.publisher.ministerialInstitute of Electrical and Electronics Engineers (IEEE)pl
dc.rightsDodaję tylko opis bibliograficzny*
dc.rights.licencebez licencji
dc.rights.uri*
dc.subject.enquantum systempl
dc.subject.enprogram processorspl
dc.subject.encomputational modelingpl
dc.subject.enquantum statepl
dc.subject.ennumerical modelspl
dc.subject.enconvolutional neural networkspl
dc.subject.enintegrated circuit modelingpl
dc.subtypeConferenceProceedingspl
dc.titleA quantum convolutional neural network for image classificationpl
dc.title.container40th Chinese Control Conference (CCC)pl
dc.typeBookSectionpl
dspace.entity.typePublication
cris.lastimport.wos
2024-04-09T22:27:48Z
dc.abstract.enpl
Artificial neural networks have achieved great success in many fields ranging from image recognition to video understanding. However, its high requirements for computing and memory resources have limited further development on processing big data with high dimensions. In recent years, advances in quantum computing show that building neural networks on quantum processors is a potential solution to this problem. In this paper, we propose a novel neural network model named Quantum Convolutional Neural Network (QCNN), aiming at utilizing the computing power of quantum systems to accelerate classical machine learning tasks. The designed QCNN is based on implementable quantum circuits and has a similar structure as classical convolutional neural networks. Numerical simulation results on the MNIST dataset demonstrate the effectiveness of our model.
dc.affiliationpl
Wydział Fizyki, Astronomii i Informatyki Stosowanej : Instytut Informatyki Stosowanej
dc.conferencepl
40th Chinese Control Conference
dc.conference.city
Szanghaj
dc.conference.country
Chiny
dc.conference.datefinish
2021-07-28
dc.conference.datestart
2021-07-26
dc.contributor.authorpl
Lü, Yanxuan
dc.contributor.authorpl
Gao, Qing
dc.contributor.authorpl
Lü, Jinhu
dc.contributor.authorpl
Ogorzałek, Maciej - 102456
dc.contributor.authorpl
Zheng, Jin
dc.contributor.editorpl
Peng, Chen
dc.contributor.editorpl
Sun, Jian
dc.date.accessioned
2022-05-09T15:01:28Z
dc.date.available
2022-05-09T15:01:28Z
dc.date.issuedpl
2021
dc.description.conftypepl
international
dc.description.physicalpl
6329-6334
dc.description.series
Chinese Control Conference
dc.identifier.doipl
10.23919/CCC52363.2021.9550027
dc.identifier.eisbnpl
978-9-8815-6380-4
dc.identifier.isbnpl
978-1-6654-1195-0
dc.identifier.serieseissn
2161-2927
dc.identifier.seriesissn
1934-1768
dc.identifier.uri
https://ruj.uj.edu.pl/xmlui/handle/item/291834
dc.languagepl
eng
dc.language.containerpl
eng
dc.pubinfopl
[s.l.] : IEEE
dc.publisher.ministerialpl
Institute of Electrical and Electronics Engineers (IEEE)
dc.rights*
Dodaję tylko opis bibliograficzny
dc.rights.licence
bez licencji
dc.rights.uri*
dc.subject.enpl
quantum system
dc.subject.enpl
program processors
dc.subject.enpl
computational modeling
dc.subject.enpl
quantum state
dc.subject.enpl
numerical models
dc.subject.enpl
convolutional neural networks
dc.subject.enpl
integrated circuit modeling
dc.subtypepl
ConferenceProceedings
dc.titlepl
A quantum convolutional neural network for image classification
dc.title.containerpl
40th Chinese Control Conference (CCC)
dc.typepl
BookSection
dspace.entity.type
Publication

* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.

Views
34
Views per month
Views per city
Ashburn
7
Overland Park
3
Guangzhou
2
Kolkata
2
Krakow
2
Tokyo
2
Wroclaw
2
Cairo
1
Dublin
1
Los Angeles
1

No access

No Thumbnail Available