Neural networks can learn to utilize correlated auxiliary noise

We demonstrate that neural networks that process noisy data can learn to exploit, when available, access to auxiliary noise that is correlated with the noise on the data. In effect, the network learns to use the correlated auxiliary noise as an approximate key to decipher its noisy input data. An ex...

Descripción completa

Detalles Bibliográficos
Autores principales: Ahmadzadegan, Aida, Simidzija, Petar, Li, Ming, Kempf, Achim
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8566565/
https://www.ncbi.nlm.nih.gov/pubmed/34732745
http://dx.doi.org/10.1038/s41598-021-00502-4
_version_ 1784594042140491776
author Ahmadzadegan, Aida
Simidzija, Petar
Li, Ming
Kempf, Achim
author_facet Ahmadzadegan, Aida
Simidzija, Petar
Li, Ming
Kempf, Achim
author_sort Ahmadzadegan, Aida
collection PubMed
description We demonstrate that neural networks that process noisy data can learn to exploit, when available, access to auxiliary noise that is correlated with the noise on the data. In effect, the network learns to use the correlated auxiliary noise as an approximate key to decipher its noisy input data. An example of naturally occurring correlated auxiliary noise is the noise due to decoherence. Our results could, therefore, also be of interest, for example, for machine-learned quantum error correction.
format Online
Article
Text
id pubmed-8566565
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-85665652021-11-05 Neural networks can learn to utilize correlated auxiliary noise Ahmadzadegan, Aida Simidzija, Petar Li, Ming Kempf, Achim Sci Rep Article We demonstrate that neural networks that process noisy data can learn to exploit, when available, access to auxiliary noise that is correlated with the noise on the data. In effect, the network learns to use the correlated auxiliary noise as an approximate key to decipher its noisy input data. An example of naturally occurring correlated auxiliary noise is the noise due to decoherence. Our results could, therefore, also be of interest, for example, for machine-learned quantum error correction. Nature Publishing Group UK 2021-11-03 /pmc/articles/PMC8566565/ /pubmed/34732745 http://dx.doi.org/10.1038/s41598-021-00502-4 Text en © The Author(s) 2021 https://creativecommons.org/licenses/by/4.0/Open AccessThis 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 licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence 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 licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Ahmadzadegan, Aida
Simidzija, Petar
Li, Ming
Kempf, Achim
Neural networks can learn to utilize correlated auxiliary noise
title Neural networks can learn to utilize correlated auxiliary noise
title_full Neural networks can learn to utilize correlated auxiliary noise
title_fullStr Neural networks can learn to utilize correlated auxiliary noise
title_full_unstemmed Neural networks can learn to utilize correlated auxiliary noise
title_short Neural networks can learn to utilize correlated auxiliary noise
title_sort neural networks can learn to utilize correlated auxiliary noise
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8566565/
https://www.ncbi.nlm.nih.gov/pubmed/34732745
http://dx.doi.org/10.1038/s41598-021-00502-4
work_keys_str_mv AT ahmadzadeganaida neuralnetworkscanlearntoutilizecorrelatedauxiliarynoise
AT simidzijapetar neuralnetworkscanlearntoutilizecorrelatedauxiliarynoise
AT liming neuralnetworkscanlearntoutilizecorrelatedauxiliarynoise
AT kempfachim neuralnetworkscanlearntoutilizecorrelatedauxiliarynoise

Ejemplares similares