Show simple item record

dc.contributor.authorBeer, Kerstin
dc.contributor.authorBondarenko, Dmytro
dc.contributor.authorFarrelly, Terry
dc.contributor.authorOsborne, Tobias J
dc.contributor.authorSalzmann, Robert
dc.contributor.authorScheiermann, Daniel
dc.contributor.authorWolf, Ramona
dc.date.accessioned2021-02-09T16:34:00Z
dc.date.available2021-02-09T16:34:00Z
dc.date.issued2020-02-10
dc.date.submitted2019-07-02
dc.identifier.issn2041-1723
dc.identifier.others41467-020-14454-2
dc.identifier.other14454
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/317404
dc.description.abstractNeural networks enjoy widespread success in both research and industry and, with the advent of quantum technology, it is a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose a truly quantum analogue of classical neurons, which form quantum feedforward neural networks capable of universal quantum computation. We describe the efficient training of these networks using the fidelity as a cost function, providing both classical and efficient quantum implementations. Our method allows for fast optimisation with reduced memory requirements: the number of qudits required scales with only the width, allowing deep-network optimisation. We benchmark our proposal for the quantum task of learning an unknown unitary and find remarkable generalisation behaviour and a striking robustness to noisy training data.
dc.languageen
dc.publisherSpringer Science and Business Media LLC
dc.rightsAttribution 4.0 International (CC BY 4.0)
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectArticle
dc.subject/639/705/1042
dc.subject/639/766/483/481
dc.subjectarticle
dc.titleTraining deep quantum neural networks.
dc.typeArticle
dc.date.updated2021-02-09T16:34:00Z
prism.issueIdentifier1
prism.publicationNameNat Commun
prism.volume11
dc.identifier.doi10.17863/CAM.64517
dcterms.dateAccepted2019-12-26
rioxxterms.versionofrecord10.1038/s41467-020-14454-2
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
dc.contributor.orcidBeer, Kerstin [0000-0002-3189-8322]
dc.contributor.orcidFarrelly, Terry [0000-0002-7662-2303]
dc.contributor.orcidWolf, Ramona [0000-0002-9404-5781]
dc.identifier.eissn2041-1723
pubs.funder-project-idDeutsche Forschungsgemeinschaft (German Research Foundation) (SFB 1227, RTG 1991, EXC 2123)
cam.issuedOnline2020-02-10


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's licence is described as Attribution 4.0 International (CC BY 4.0)