Photorefractive Integrated Photonics for Analog Signal Processing in AI
The computational cost of AI could be alleviated by accelerating the synaptic transfer calculations in artificial neural networks with an analog crossbar array processor. In this work, we present the core building blocks of an all-optical integrated photorefractive crossbar array for artificial neur...
Gespeichert in:
| Veröffentlicht in: | IEEE journal of selected topics in quantum electronics 2025-05, Vol.31 (3: AI/ML Integrated Opto-electronics), p.1-10 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 10 |
|---|---|
| container_issue | 3: AI/ML Integrated Opto-electronics |
| container_start_page | 1 |
| container_title | IEEE journal of selected topics in quantum electronics |
| container_volume | 31 |
| creator | Vlieg, Elger A. Dangel, Roger Offrein, Bert J. Horst, Folkert |
| description | The computational cost of AI could be alleviated by accelerating the synaptic transfer calculations in artificial neural networks with an analog crossbar array processor. In this work, we present the core building blocks of an all-optical integrated photorefractive crossbar array for artificial neural network training by demonstrating photorefractive synapses in an integrated 2-D beam interaction network. We show that the photorefractive quality of the circuits resembles that of the bulk GaAs crystal that they were fabricated from. Then, this work experimentally validates the integrated photorefractive crossbar array design and constitutes a framework for engineering photorefractive integrated photonics. |
| doi_str_mv | 10.1109/JSTQE.2024.3519983 |
| format | Article |
| fullrecord | <record><control><sourceid>crossref_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10806637</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10806637</ieee_id><sourcerecordid>10_1109_JSTQE_2024_3519983</sourcerecordid><originalsourceid>FETCH-LOGICAL-c149t-b4f34847d256139716be119e4fea2522518eeb3ce7c0980c72a5f84120fe27773</originalsourceid><addsrcrecordid>eNpNkM1KAzEUhYMoWKsvIC7yAlNv_ibJspTaVgpWWsHdkKY3Y6TOSDIIvr3Tn4Wre-DyHQ4fIfcMRoyBfXxeb16nIw5cjoRi1hpxQQZMKVNIJflln0Hrgpfwfk1ucv4EACMNDMhs9dF2bcKQnO_iD9JF02GdXIc7enw10Wca2kTHjdu3NV3Hug90lVqPOcemprGh48UtuQpun_HufIfk7Wm6mcyL5ctsMRkvC8-k7YqtDEIaqXdclUxYzcotMmZRBnRcca6YQdwKj9qDNeA1dyoYyTgE5FprMST81OtTm3O_u_pO8cul34pBdVBRHVVUBxXVWUUPPZygiIj_AANlKbT4A0P_Wpc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Photorefractive Integrated Photonics for Analog Signal Processing in AI</title><source>IEEE Electronic Library (IEL)</source><creator>Vlieg, Elger A. ; Dangel, Roger ; Offrein, Bert J. ; Horst, Folkert</creator><creatorcontrib>Vlieg, Elger A. ; Dangel, Roger ; Offrein, Bert J. ; Horst, Folkert</creatorcontrib><description>The computational cost of AI could be alleviated by accelerating the synaptic transfer calculations in artificial neural networks with an analog crossbar array processor. In this work, we present the core building blocks of an all-optical integrated photorefractive crossbar array for artificial neural network training by demonstrating photorefractive synapses in an integrated 2-D beam interaction network. We show that the photorefractive quality of the circuits resembles that of the bulk GaAs crystal that they were fabricated from. Then, this work experimentally validates the integrated photorefractive crossbar array design and constitutes a framework for engineering photorefractive integrated photonics.</description><identifier>ISSN: 1077-260X</identifier><identifier>EISSN: 1558-4542</identifier><identifier>DOI: 10.1109/JSTQE.2024.3519983</identifier><identifier>CODEN: IJSQEN</identifier><language>eng</language><publisher>IEEE</publisher><subject>Analog crossbar multiply-accumulate (MAC) accelerator ; Artificial neural networks ; Bragg gratings ; Diffraction ; Gallium arsenide ; holographic photonic memory ; in-memory computing ; integrated photonics ; Laser beams ; Optical device fabrication ; Optical mixing ; Photonics ; photorefractive effect ; Synapses ; Vectors</subject><ispartof>IEEE journal of selected topics in quantum electronics, 2025-05, Vol.31 (3: AI/ML Integrated Opto-electronics), p.1-10</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c149t-b4f34847d256139716be119e4fea2522518eeb3ce7c0980c72a5f84120fe27773</cites><orcidid>0000-0002-7222-7963 ; 0000-0001-6082-0068 ; 0000-0002-6986-9973 ; 0000-0001-6559-2076</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10806637$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids></links><search><creatorcontrib>Vlieg, Elger A.</creatorcontrib><creatorcontrib>Dangel, Roger</creatorcontrib><creatorcontrib>Offrein, Bert J.</creatorcontrib><creatorcontrib>Horst, Folkert</creatorcontrib><title>Photorefractive Integrated Photonics for Analog Signal Processing in AI</title><title>IEEE journal of selected topics in quantum electronics</title><addtitle>JSTQE</addtitle><description>The computational cost of AI could be alleviated by accelerating the synaptic transfer calculations in artificial neural networks with an analog crossbar array processor. In this work, we present the core building blocks of an all-optical integrated photorefractive crossbar array for artificial neural network training by demonstrating photorefractive synapses in an integrated 2-D beam interaction network. We show that the photorefractive quality of the circuits resembles that of the bulk GaAs crystal that they were fabricated from. Then, this work experimentally validates the integrated photorefractive crossbar array design and constitutes a framework for engineering photorefractive integrated photonics.</description><subject>Analog crossbar multiply-accumulate (MAC) accelerator</subject><subject>Artificial neural networks</subject><subject>Bragg gratings</subject><subject>Diffraction</subject><subject>Gallium arsenide</subject><subject>holographic photonic memory</subject><subject>in-memory computing</subject><subject>integrated photonics</subject><subject>Laser beams</subject><subject>Optical device fabrication</subject><subject>Optical mixing</subject><subject>Photonics</subject><subject>photorefractive effect</subject><subject>Synapses</subject><subject>Vectors</subject><issn>1077-260X</issn><issn>1558-4542</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2025</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><recordid>eNpNkM1KAzEUhYMoWKsvIC7yAlNv_ibJspTaVgpWWsHdkKY3Y6TOSDIIvr3Tn4Wre-DyHQ4fIfcMRoyBfXxeb16nIw5cjoRi1hpxQQZMKVNIJflln0Hrgpfwfk1ucv4EACMNDMhs9dF2bcKQnO_iD9JF02GdXIc7enw10Wca2kTHjdu3NV3Hug90lVqPOcemprGh48UtuQpun_HufIfk7Wm6mcyL5ctsMRkvC8-k7YqtDEIaqXdclUxYzcotMmZRBnRcca6YQdwKj9qDNeA1dyoYyTgE5FprMST81OtTm3O_u_pO8cul34pBdVBRHVVUBxXVWUUPPZygiIj_AANlKbT4A0P_Wpc</recordid><startdate>202505</startdate><enddate>202505</enddate><creator>Vlieg, Elger A.</creator><creator>Dangel, Roger</creator><creator>Offrein, Bert J.</creator><creator>Horst, Folkert</creator><general>IEEE</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-7222-7963</orcidid><orcidid>https://orcid.org/0000-0001-6082-0068</orcidid><orcidid>https://orcid.org/0000-0002-6986-9973</orcidid><orcidid>https://orcid.org/0000-0001-6559-2076</orcidid></search><sort><creationdate>202505</creationdate><title>Photorefractive Integrated Photonics for Analog Signal Processing in AI</title><author>Vlieg, Elger A. ; Dangel, Roger ; Offrein, Bert J. ; Horst, Folkert</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c149t-b4f34847d256139716be119e4fea2522518eeb3ce7c0980c72a5f84120fe27773</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2025</creationdate><topic>Analog crossbar multiply-accumulate (MAC) accelerator</topic><topic>Artificial neural networks</topic><topic>Bragg gratings</topic><topic>Diffraction</topic><topic>Gallium arsenide</topic><topic>holographic photonic memory</topic><topic>in-memory computing</topic><topic>integrated photonics</topic><topic>Laser beams</topic><topic>Optical device fabrication</topic><topic>Optical mixing</topic><topic>Photonics</topic><topic>photorefractive effect</topic><topic>Synapses</topic><topic>Vectors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Vlieg, Elger A.</creatorcontrib><creatorcontrib>Dangel, Roger</creatorcontrib><creatorcontrib>Offrein, Bert J.</creatorcontrib><creatorcontrib>Horst, Folkert</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><jtitle>IEEE journal of selected topics in quantum electronics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Vlieg, Elger A.</au><au>Dangel, Roger</au><au>Offrein, Bert J.</au><au>Horst, Folkert</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Photorefractive Integrated Photonics for Analog Signal Processing in AI</atitle><jtitle>IEEE journal of selected topics in quantum electronics</jtitle><stitle>JSTQE</stitle><date>2025-05</date><risdate>2025</risdate><volume>31</volume><issue>3: AI/ML Integrated Opto-electronics</issue><spage>1</spage><epage>10</epage><pages>1-10</pages><issn>1077-260X</issn><eissn>1558-4542</eissn><coden>IJSQEN</coden><abstract>The computational cost of AI could be alleviated by accelerating the synaptic transfer calculations in artificial neural networks with an analog crossbar array processor. In this work, we present the core building blocks of an all-optical integrated photorefractive crossbar array for artificial neural network training by demonstrating photorefractive synapses in an integrated 2-D beam interaction network. We show that the photorefractive quality of the circuits resembles that of the bulk GaAs crystal that they were fabricated from. Then, this work experimentally validates the integrated photorefractive crossbar array design and constitutes a framework for engineering photorefractive integrated photonics.</abstract><pub>IEEE</pub><doi>10.1109/JSTQE.2024.3519983</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-7222-7963</orcidid><orcidid>https://orcid.org/0000-0001-6082-0068</orcidid><orcidid>https://orcid.org/0000-0002-6986-9973</orcidid><orcidid>https://orcid.org/0000-0001-6559-2076</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1077-260X |
| ispartof | IEEE journal of selected topics in quantum electronics, 2025-05, Vol.31 (3: AI/ML Integrated Opto-electronics), p.1-10 |
| issn | 1077-260X 1558-4542 |
| language | eng |
| recordid | cdi_ieee_primary_10806637 |
| source | IEEE Electronic Library (IEL) |
| subjects | Analog crossbar multiply-accumulate (MAC) accelerator Artificial neural networks Bragg gratings Diffraction Gallium arsenide holographic photonic memory in-memory computing integrated photonics Laser beams Optical device fabrication Optical mixing Photonics photorefractive effect Synapses Vectors |
| title | Photorefractive Integrated Photonics for Analog Signal Processing in AI |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T07%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_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Photorefractive%20Integrated%20Photonics%20for%20Analog%20Signal%20Processing%20in%20AI&rft.jtitle=IEEE%20journal%20of%20selected%20topics%20in%20quantum%20electronics&rft.au=Vlieg,%20Elger%20A.&rft.date=2025-05&rft.volume=31&rft.issue=3:%20AI/ML%20Integrated%20Opto-electronics&rft.spage=1&rft.epage=10&rft.pages=1-10&rft.issn=1077-260X&rft.eissn=1558-4542&rft.coden=IJSQEN&rft_id=info:doi/10.1109/JSTQE.2024.3519983&rft_dat=%3Ccrossref_ieee_%3E10_1109_JSTQE_2024_3519983%3C/crossref_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10806637&rfr_iscdi=true |