Loading…

All-optical neuromorphic binary convolution with a spiking VCSEL neuron for image gradient magnitudes

All-optical binary convolution with a photonic spiking vertical-cavity surface-emitting laser (VCSEL) neuron is proposed and demonstrated experimentally for the first time, to the best of our knowledge. Optical inputs, extracted from digital images and temporally encoded using rectangular pulses, ar...

Full description

Saved in:
Bibliographic Details
Published in:Photonics research (Washington, DC) DC), 2021-05, Vol.9 (5), p.B201
Main Authors: Zhang, Yahui, Robertson, Joshua, Xiang, Shuiying, Hejda, Matěj, Bueno, Julián, Hurtado, Antonio
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c267t-5215ef3dcf018288a9f187e31a4bef6dfbfd7aac7e43f6374a401a7584725af43
cites cdi_FETCH-LOGICAL-c267t-5215ef3dcf018288a9f187e31a4bef6dfbfd7aac7e43f6374a401a7584725af43
container_end_page
container_issue 5
container_start_page B201
container_title Photonics research (Washington, DC)
container_volume 9
creator Zhang, Yahui
Robertson, Joshua
Xiang, Shuiying
Hejda, Matěj
Bueno, Julián
Hurtado, Antonio
description All-optical binary convolution with a photonic spiking vertical-cavity surface-emitting laser (VCSEL) neuron is proposed and demonstrated experimentally for the first time, to the best of our knowledge. Optical inputs, extracted from digital images and temporally encoded using rectangular pulses, are injected in the VCSEL neuron, which delivers the convolution result in the number of fast ( < 100    ps long) spikes fired. Experimental and numerical results show that binary convolution is achieved successfully with a single spiking VCSEL neuron and that all-optical binary convolution can be used to calculate image gradient magnitudes to detect edge features and separate vertical and horizontal components in source images. We also show that this all-optical spiking binary convolution system is robust to noise and can operate with high-resolution images. Additionally, the proposed system offers important advantages such as ultrafast speed, high-energy efficiency, and simple hardware implementation, highlighting the potentials of spiking photonic VCSEL neurons for high-speed neuromorphic image processing systems and future photonic spiking convolutional neural networks.
doi_str_mv 10.1364/PRJ.412141
format article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1364_PRJ_412141</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1364_PRJ_412141</sourcerecordid><originalsourceid>FETCH-LOGICAL-c267t-5215ef3dcf018288a9f187e31a4bef6dfbfd7aac7e43f6374a401a7584725af43</originalsourceid><addsrcrecordid>eNpNkEtPwzAQhC0EElXphV_gM1JK1nbi5FhF5aVIIF7XaOvYqSG1IzsF9d8TVA7MZWYOs1p9hFxCugSei-un54elAAYCTsiMcSaTElh2-i-fk0WMH-mkUgDP8hnRq75P_DBahT11eh_8zodhaxXdWIfhQJV3X77fj9Y7-m3HLUUaB_tpXUffq5d1fRw5anygdoedpl3A1mo30qk5O-5bHS_ImcE-6sWfz8nbzfq1ukvqx9v7alUniuVyTDIGmTa8VSaFghUFlgYKqTmg2GiTt2ZjWomopBbc5FwKFCmgzAohWYZG8Dm5Ot5VwccYtGmGMD0VDg2kzS-jZmLUHBnxHxYBWww</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>All-optical neuromorphic binary convolution with a spiking VCSEL neuron for image gradient magnitudes</title><source>EZB-FREE-00999 freely available EZB journals</source><creator>Zhang, Yahui ; Robertson, Joshua ; Xiang, Shuiying ; Hejda, Matěj ; Bueno, Julián ; Hurtado, Antonio</creator><creatorcontrib>Zhang, Yahui ; Robertson, Joshua ; Xiang, Shuiying ; Hejda, Matěj ; Bueno, Julián ; Hurtado, Antonio</creatorcontrib><description>All-optical binary convolution with a photonic spiking vertical-cavity surface-emitting laser (VCSEL) neuron is proposed and demonstrated experimentally for the first time, to the best of our knowledge. Optical inputs, extracted from digital images and temporally encoded using rectangular pulses, are injected in the VCSEL neuron, which delivers the convolution result in the number of fast ( &lt; 100    ps long) spikes fired. Experimental and numerical results show that binary convolution is achieved successfully with a single spiking VCSEL neuron and that all-optical binary convolution can be used to calculate image gradient magnitudes to detect edge features and separate vertical and horizontal components in source images. We also show that this all-optical spiking binary convolution system is robust to noise and can operate with high-resolution images. Additionally, the proposed system offers important advantages such as ultrafast speed, high-energy efficiency, and simple hardware implementation, highlighting the potentials of spiking photonic VCSEL neurons for high-speed neuromorphic image processing systems and future photonic spiking convolutional neural networks.</description><identifier>ISSN: 2327-9125</identifier><identifier>EISSN: 2327-9125</identifier><identifier>DOI: 10.1364/PRJ.412141</identifier><language>eng</language><ispartof>Photonics research (Washington, DC), 2021-05, Vol.9 (5), p.B201</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c267t-5215ef3dcf018288a9f187e31a4bef6dfbfd7aac7e43f6374a401a7584725af43</citedby><cites>FETCH-LOGICAL-c267t-5215ef3dcf018288a9f187e31a4bef6dfbfd7aac7e43f6374a401a7584725af43</cites><orcidid>0000-0003-2605-6494 ; 0000-0001-6316-5265</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Zhang, Yahui</creatorcontrib><creatorcontrib>Robertson, Joshua</creatorcontrib><creatorcontrib>Xiang, Shuiying</creatorcontrib><creatorcontrib>Hejda, Matěj</creatorcontrib><creatorcontrib>Bueno, Julián</creatorcontrib><creatorcontrib>Hurtado, Antonio</creatorcontrib><title>All-optical neuromorphic binary convolution with a spiking VCSEL neuron for image gradient magnitudes</title><title>Photonics research (Washington, DC)</title><description>All-optical binary convolution with a photonic spiking vertical-cavity surface-emitting laser (VCSEL) neuron is proposed and demonstrated experimentally for the first time, to the best of our knowledge. Optical inputs, extracted from digital images and temporally encoded using rectangular pulses, are injected in the VCSEL neuron, which delivers the convolution result in the number of fast ( &lt; 100    ps long) spikes fired. Experimental and numerical results show that binary convolution is achieved successfully with a single spiking VCSEL neuron and that all-optical binary convolution can be used to calculate image gradient magnitudes to detect edge features and separate vertical and horizontal components in source images. We also show that this all-optical spiking binary convolution system is robust to noise and can operate with high-resolution images. Additionally, the proposed system offers important advantages such as ultrafast speed, high-energy efficiency, and simple hardware implementation, highlighting the potentials of spiking photonic VCSEL neurons for high-speed neuromorphic image processing systems and future photonic spiking convolutional neural networks.</description><issn>2327-9125</issn><issn>2327-9125</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNpNkEtPwzAQhC0EElXphV_gM1JK1nbi5FhF5aVIIF7XaOvYqSG1IzsF9d8TVA7MZWYOs1p9hFxCugSei-un54elAAYCTsiMcSaTElh2-i-fk0WMH-mkUgDP8hnRq75P_DBahT11eh_8zodhaxXdWIfhQJV3X77fj9Y7-m3HLUUaB_tpXUffq5d1fRw5anygdoedpl3A1mo30qk5O-5bHS_ImcE-6sWfz8nbzfq1ukvqx9v7alUniuVyTDIGmTa8VSaFghUFlgYKqTmg2GiTt2ZjWomopBbc5FwKFCmgzAohWYZG8Dm5Ot5VwccYtGmGMD0VDg2kzS-jZmLUHBnxHxYBWww</recordid><startdate>20210501</startdate><enddate>20210501</enddate><creator>Zhang, Yahui</creator><creator>Robertson, Joshua</creator><creator>Xiang, Shuiying</creator><creator>Hejda, Matěj</creator><creator>Bueno, Julián</creator><creator>Hurtado, Antonio</creator><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-2605-6494</orcidid><orcidid>https://orcid.org/0000-0001-6316-5265</orcidid></search><sort><creationdate>20210501</creationdate><title>All-optical neuromorphic binary convolution with a spiking VCSEL neuron for image gradient magnitudes</title><author>Zhang, Yahui ; Robertson, Joshua ; Xiang, Shuiying ; Hejda, Matěj ; Bueno, Julián ; Hurtado, Antonio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c267t-5215ef3dcf018288a9f187e31a4bef6dfbfd7aac7e43f6374a401a7584725af43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Yahui</creatorcontrib><creatorcontrib>Robertson, Joshua</creatorcontrib><creatorcontrib>Xiang, Shuiying</creatorcontrib><creatorcontrib>Hejda, Matěj</creatorcontrib><creatorcontrib>Bueno, Julián</creatorcontrib><creatorcontrib>Hurtado, Antonio</creatorcontrib><collection>CrossRef</collection><jtitle>Photonics research (Washington, DC)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Yahui</au><au>Robertson, Joshua</au><au>Xiang, Shuiying</au><au>Hejda, Matěj</au><au>Bueno, Julián</au><au>Hurtado, Antonio</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>All-optical neuromorphic binary convolution with a spiking VCSEL neuron for image gradient magnitudes</atitle><jtitle>Photonics research (Washington, DC)</jtitle><date>2021-05-01</date><risdate>2021</risdate><volume>9</volume><issue>5</issue><spage>B201</spage><pages>B201-</pages><issn>2327-9125</issn><eissn>2327-9125</eissn><abstract>All-optical binary convolution with a photonic spiking vertical-cavity surface-emitting laser (VCSEL) neuron is proposed and demonstrated experimentally for the first time, to the best of our knowledge. Optical inputs, extracted from digital images and temporally encoded using rectangular pulses, are injected in the VCSEL neuron, which delivers the convolution result in the number of fast ( &lt; 100    ps long) spikes fired. Experimental and numerical results show that binary convolution is achieved successfully with a single spiking VCSEL neuron and that all-optical binary convolution can be used to calculate image gradient magnitudes to detect edge features and separate vertical and horizontal components in source images. We also show that this all-optical spiking binary convolution system is robust to noise and can operate with high-resolution images. Additionally, the proposed system offers important advantages such as ultrafast speed, high-energy efficiency, and simple hardware implementation, highlighting the potentials of spiking photonic VCSEL neurons for high-speed neuromorphic image processing systems and future photonic spiking convolutional neural networks.</abstract><doi>10.1364/PRJ.412141</doi><orcidid>https://orcid.org/0000-0003-2605-6494</orcidid><orcidid>https://orcid.org/0000-0001-6316-5265</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2327-9125
ispartof Photonics research (Washington, DC), 2021-05, Vol.9 (5), p.B201
issn 2327-9125
2327-9125
language eng
recordid cdi_crossref_primary_10_1364_PRJ_412141
source EZB-FREE-00999 freely available EZB journals
title All-optical neuromorphic binary convolution with a spiking VCSEL neuron for image gradient magnitudes
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T13%3A19%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=All-optical%20neuromorphic%20binary%20convolution%20with%20a%20spiking%20VCSEL%20neuron%20for%20image%20gradient%20magnitudes&rft.jtitle=Photonics%20research%20(Washington,%20DC)&rft.au=Zhang,%20Yahui&rft.date=2021-05-01&rft.volume=9&rft.issue=5&rft.spage=B201&rft.pages=B201-&rft.issn=2327-9125&rft.eissn=2327-9125&rft_id=info:doi/10.1364/PRJ.412141&rft_dat=%3Ccrossref%3E10_1364_PRJ_412141%3C/crossref%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c267t-5215ef3dcf018288a9f187e31a4bef6dfbfd7aac7e43f6374a401a7584725af43%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true