Cargando…

Integrated photonic metasystem for image classifications at telecommunication wavelength

Miniaturized image classifiers are potential for revolutionizing their applications in optical communication, autonomous vehicles, and healthcare. With subwavelength structure enabled directional diffraction and dispersion engineering, the light propagation through multi-layer metasurfaces achieves...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Zi, Chang, Lorry, Wang, Feifan, Li, Tiantian, Gu, Tingyi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9018697/
https://www.ncbi.nlm.nih.gov/pubmed/35440131
http://dx.doi.org/10.1038/s41467-022-29856-7
_version_ 1784689078708469760
author Wang, Zi
Chang, Lorry
Wang, Feifan
Li, Tiantian
Gu, Tingyi
author_facet Wang, Zi
Chang, Lorry
Wang, Feifan
Li, Tiantian
Gu, Tingyi
author_sort Wang, Zi
collection PubMed
description Miniaturized image classifiers are potential for revolutionizing their applications in optical communication, autonomous vehicles, and healthcare. With subwavelength structure enabled directional diffraction and dispersion engineering, the light propagation through multi-layer metasurfaces achieves wavelength-selective image recognitions on a silicon photonic platform at telecommunication wavelength. The metasystems implement high-throughput vector-by-matrix multiplications, enabled by near 10(3) nanoscale phase shifters as weight elements within 0.135 mm(2) footprints. The diffraction manifested computing capability incorporates the fabrication and measurement related phase fluctuations, and thus the pre-trained metasystem can handle uncertainties in inputs without post-tuning. Here we demonstrate three functional metasystems: a 15-pixel spatial pattern classifier that reaches near 90% accuracy with femtosecond inputs, a multi-channel wavelength demultiplexer, and a hyperspectral image classifier. The diffractive metasystem provides an alternative machine learning architecture for photonic integrated circuits, with densely integrated phase shifters, spatially multiplexed throughput, and data processing capabilities.
format Online
Article
Text
id pubmed-9018697
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-90186972022-04-28 Integrated photonic metasystem for image classifications at telecommunication wavelength Wang, Zi Chang, Lorry Wang, Feifan Li, Tiantian Gu, Tingyi Nat Commun Article Miniaturized image classifiers are potential for revolutionizing their applications in optical communication, autonomous vehicles, and healthcare. With subwavelength structure enabled directional diffraction and dispersion engineering, the light propagation through multi-layer metasurfaces achieves wavelength-selective image recognitions on a silicon photonic platform at telecommunication wavelength. The metasystems implement high-throughput vector-by-matrix multiplications, enabled by near 10(3) nanoscale phase shifters as weight elements within 0.135 mm(2) footprints. The diffraction manifested computing capability incorporates the fabrication and measurement related phase fluctuations, and thus the pre-trained metasystem can handle uncertainties in inputs without post-tuning. Here we demonstrate three functional metasystems: a 15-pixel spatial pattern classifier that reaches near 90% accuracy with femtosecond inputs, a multi-channel wavelength demultiplexer, and a hyperspectral image classifier. The diffractive metasystem provides an alternative machine learning architecture for photonic integrated circuits, with densely integrated phase shifters, spatially multiplexed throughput, and data processing capabilities. Nature Publishing Group UK 2022-04-19 /pmc/articles/PMC9018697/ /pubmed/35440131 http://dx.doi.org/10.1038/s41467-022-29856-7 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/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/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Wang, Zi
Chang, Lorry
Wang, Feifan
Li, Tiantian
Gu, Tingyi
Integrated photonic metasystem for image classifications at telecommunication wavelength
title Integrated photonic metasystem for image classifications at telecommunication wavelength
title_full Integrated photonic metasystem for image classifications at telecommunication wavelength
title_fullStr Integrated photonic metasystem for image classifications at telecommunication wavelength
title_full_unstemmed Integrated photonic metasystem for image classifications at telecommunication wavelength
title_short Integrated photonic metasystem for image classifications at telecommunication wavelength
title_sort integrated photonic metasystem for image classifications at telecommunication wavelength
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9018697/
https://www.ncbi.nlm.nih.gov/pubmed/35440131
http://dx.doi.org/10.1038/s41467-022-29856-7
work_keys_str_mv AT wangzi integratedphotonicmetasystemforimageclassificationsattelecommunicationwavelength
AT changlorry integratedphotonicmetasystemforimageclassificationsattelecommunicationwavelength
AT wangfeifan integratedphotonicmetasystemforimageclassificationsattelecommunicationwavelength
AT litiantian integratedphotonicmetasystemforimageclassificationsattelecommunicationwavelength
AT gutingyi integratedphotonicmetasystemforimageclassificationsattelecommunicationwavelength