Cargando…

Photonic Matrix Computing: From Fundamentals to Applications

In emerging artificial intelligence applications, massive matrix operations require high computing speed and energy efficiency. Optical computing can realize high-speed parallel information processing with ultra-low energy consumption on photonic integrated platforms or in free space, which can well...

Descripción completa

Detalles Bibliográficos
Autores principales: Cheng, Junwei, Zhou, Hailong, Dong, Jianji
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8308143/
https://www.ncbi.nlm.nih.gov/pubmed/34206814
http://dx.doi.org/10.3390/nano11071683
_version_ 1783728210811289600
author Cheng, Junwei
Zhou, Hailong
Dong, Jianji
author_facet Cheng, Junwei
Zhou, Hailong
Dong, Jianji
author_sort Cheng, Junwei
collection PubMed
description In emerging artificial intelligence applications, massive matrix operations require high computing speed and energy efficiency. Optical computing can realize high-speed parallel information processing with ultra-low energy consumption on photonic integrated platforms or in free space, which can well meet these domain-specific demands. In this review, we firstly introduce the principles of photonic matrix computing implemented by three mainstream schemes, and then review the research progress of optical neural networks (ONNs) based on photonic matrix computing. In addition, we discuss the advantages of optical computing architectures over electronic processors as well as current challenges of optical computing and highlight some promising prospects for the future development.
format Online
Article
Text
id pubmed-8308143
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83081432021-07-25 Photonic Matrix Computing: From Fundamentals to Applications Cheng, Junwei Zhou, Hailong Dong, Jianji Nanomaterials (Basel) Review In emerging artificial intelligence applications, massive matrix operations require high computing speed and energy efficiency. Optical computing can realize high-speed parallel information processing with ultra-low energy consumption on photonic integrated platforms or in free space, which can well meet these domain-specific demands. In this review, we firstly introduce the principles of photonic matrix computing implemented by three mainstream schemes, and then review the research progress of optical neural networks (ONNs) based on photonic matrix computing. In addition, we discuss the advantages of optical computing architectures over electronic processors as well as current challenges of optical computing and highlight some promising prospects for the future development. MDPI 2021-06-26 /pmc/articles/PMC8308143/ /pubmed/34206814 http://dx.doi.org/10.3390/nano11071683 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Review
Cheng, Junwei
Zhou, Hailong
Dong, Jianji
Photonic Matrix Computing: From Fundamentals to Applications
title Photonic Matrix Computing: From Fundamentals to Applications
title_full Photonic Matrix Computing: From Fundamentals to Applications
title_fullStr Photonic Matrix Computing: From Fundamentals to Applications
title_full_unstemmed Photonic Matrix Computing: From Fundamentals to Applications
title_short Photonic Matrix Computing: From Fundamentals to Applications
title_sort photonic matrix computing: from fundamentals to applications
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8308143/
https://www.ncbi.nlm.nih.gov/pubmed/34206814
http://dx.doi.org/10.3390/nano11071683
work_keys_str_mv AT chengjunwei photonicmatrixcomputingfromfundamentalstoapplications
AT zhouhailong photonicmatrixcomputingfromfundamentalstoapplications
AT dongjianji photonicmatrixcomputingfromfundamentalstoapplications