Cargando…

Training deep quantum neural networks

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 feedforwa...

Descripción completa

Detalles Bibliográficos
Autores principales: Beer, Kerstin, Bondarenko, Dmytro, Farrelly, Terry, Osborne, Tobias J., Salzmann, Robert, Scheiermann, Daniel, Wolf, Ramona
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7010779/
https://www.ncbi.nlm.nih.gov/pubmed/32041956
http://dx.doi.org/10.1038/s41467-020-14454-2
_version_ 1783495940797104128
author Beer, Kerstin
Bondarenko, Dmytro
Farrelly, Terry
Osborne, Tobias J.
Salzmann, Robert
Scheiermann, Daniel
Wolf, Ramona
author_facet Beer, Kerstin
Bondarenko, Dmytro
Farrelly, Terry
Osborne, Tobias J.
Salzmann, Robert
Scheiermann, Daniel
Wolf, Ramona
author_sort Beer, Kerstin
collection PubMed
description 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.
format Online
Article
Text
id pubmed-7010779
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-70107792020-02-12 Training deep quantum neural networks Beer, Kerstin Bondarenko, Dmytro Farrelly, Terry Osborne, Tobias J. Salzmann, Robert Scheiermann, Daniel Wolf, Ramona Nat Commun Article 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. Nature Publishing Group UK 2020-02-10 /pmc/articles/PMC7010779/ /pubmed/32041956 http://dx.doi.org/10.1038/s41467-020-14454-2 Text en © The Author(s) 2020 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
spellingShingle Article
Beer, Kerstin
Bondarenko, Dmytro
Farrelly, Terry
Osborne, Tobias J.
Salzmann, Robert
Scheiermann, Daniel
Wolf, Ramona
Training deep quantum neural networks
title Training deep quantum neural networks
title_full Training deep quantum neural networks
title_fullStr Training deep quantum neural networks
title_full_unstemmed Training deep quantum neural networks
title_short Training deep quantum neural networks
title_sort training deep quantum neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7010779/
https://www.ncbi.nlm.nih.gov/pubmed/32041956
http://dx.doi.org/10.1038/s41467-020-14454-2
work_keys_str_mv AT beerkerstin trainingdeepquantumneuralnetworks
AT bondarenkodmytro trainingdeepquantumneuralnetworks
AT farrellyterry trainingdeepquantumneuralnetworks
AT osbornetobiasj trainingdeepquantumneuralnetworks
AT salzmannrobert trainingdeepquantumneuralnetworks
AT scheiermanndaniel trainingdeepquantumneuralnetworks
AT wolframona trainingdeepquantumneuralnetworks