Show simple item record

dc.identifier.uri http://dx.doi.org/10.15488/9906
dc.identifier.uri https://www.repo.uni-hannover.de/handle/123456789/9964
dc.contributor.author Beer, Kerstin
dc.contributor.author Bondarenko, Dmytro
dc.contributor.author Farrelly, Terry
dc.contributor.author Osborne, Tobias J.
dc.contributor.author Salzmann, Robert
dc.contributor.author Scheiermann, Daniel
dc.contributor.author Wolf, Ramona
dc.date.accessioned 2020-06-29T15:21:49Z
dc.date.available 2020-06-29T15:21:49Z
dc.date.issued 2020
dc.identifier.citation Beer, K.; Bondarenko, D.; Farrelly, T.; Osborne, T.J.; Salzmann, R. et al.: Training deep quantum neural networks. In: Nature Communications 11 (2020), Nr. 1, 808. DOI: https://doi.org/10.1038/s41467-020-14454-2
dc.description.abstract Neural 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.language.iso eng
dc.publisher Berlin : Nature Research
dc.relation.ispartofseries Nature Communications 11 (2020), Nr. 1
dc.relation.uri https://doi.org/10.1038/s41467-020-14454-2
dc.rights CC BY 4.0 Unported
dc.rights.uri https://creativecommons.org/licenses/by/4.0/
dc.subject computer simulation eng
dc.subject design eng
dc.subject learning eng
dc.subject optimization eng
dc.subject quantum mechanics eng
dc.subject research work eng
dc.subject training eng
dc.subject article eng
dc.subject feed forward neural network eng
dc.subject learning eng
dc.subject memory eng
dc.subject nerve cell eng
dc.subject.ddc 530 | Physik ger
dc.title Training deep quantum neural networks
dc.type article
dc.type Text
dc.relation.issn 2041-1723
dc.bibliographicCitation.issue 1
dc.bibliographicCitation.volume 11
dc.bibliographicCitation.firstPage 808
tib.accessRights frei zug�nglich


Files in this item

This item appears in the following Collection(s):

Show simple item record

 

Search the repository


Browse

My Account

Usage Statistics