An on-chip programmable diffractive deep neural network based on Sb2Se3-incorporated silicon metalines

An on-chip programmable diffractive deep neural network based on Sb2Se3-incorporated silicon metalines | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article An on-chip programmable diffractive deep neural network based on Sb 2 Se 3 -incorporated silicon metalines Sanaz Zarei, Ali Ghazizadeh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4277216/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Artificial intelligence is a technology for simulating and extending human intelligence and has rapidly altered many aspects of modern society. Optical processors, which compute with photons instead of electrons, can fundamentally accelerate the development of artificial intelligence by offering substantially improved computing performance. Photonic approaches for demonstrating artificial neural networks as one of the most widely used frameworks in artificial intelligence, show extraordinary potential to achieve brain-inspired information processing at the speed of light. Recently, all-optical diffractive deep neural networks have been created that are based on passive structures and can perform complicated functions designed by computer-based neural networks. However, existing passive diffractive deep neural networks are not reconfigurable and once is fabricated, its function is fixed. This work reports an on-chip programmable deep diffractive neural network (OPD 2 NN), in which the optical neurons are built with Sb 2 Se 3 phase change material, making the network reconfigurable and non-volatile. Using numerical simulations, the performance of the OPD 2 NN is benchmarked on two machine learning tasks that are learning a multifunctional (AND-OR-NOT) logic gate and classification of images of handwritten digits from the MNIST dataset and the obtained results are validated using FDTD simulations by a commercially available full-wave electromagnetic solver. Both numerical and FDTD simulations indicate that a five-hidden-layer OPD 2 NN with a footprint of 30μmx150μm can appropriately handle (AND-OR-NOT) logic functions. For handwritten digits (0-1-2-3) classification, a three-hidden-layer OPD 2 NN with a footprint of 60μmx105μm can achieve numerical testing accuracy of 91.5% on the test dataset and the FDTD verification results show 73% matching with numerical testing results. Programmable optical neural network Diffractive deep neural network Sb2Se3-incorporated silicon metalines Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4277216","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":291979047,"identity":"2201d374-0977-44fd-ad7f-fef52858559d","order_by":0,"name":"Sanaz Zarei","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxUlEQVRIiWNgGAWjYNACAxsGAyB1oIKBgbGBSC1pEC1niNfCcBishYEoLfL9h599+FBw3t6c/ezDAwcYbGQ3HCDkpAPHjGfOMLiduLMn3QCoJc2YsBbGBmNmHoPbCQYH0hgOf2A4nEhQi3wz+2fmPwbn7A3OP2MA2vKfsBaGYzzGzEDnMW64kQbScoCwFoMzPMWMPQbJiRtugGwxSDaeSdBh/cc3M/z4Ywd0WBrzhwMVdrJ9BB2GZilpykfBKBgFo2AU4AAAZtVJSWaOPiAAAAAASUVORK5CYII=","orcid":"","institution":"Sharif University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Sanaz","middleName":"","lastName":"Zarei","suffix":""},{"id":291979297,"identity":"6a40c479-f645-489a-a7b1-4d2ed73f3b69","order_by":1,"name":"Ali Ghazizadeh","email":"","orcid":"","institution":"Sharif University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Ali","middleName":"","lastName":"Ghazizadeh","suffix":""}],"badges":[],"createdAt":"2024-04-16 15:57:02","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4277216/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4277216/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54802465,"identity":"103705af-79ed-4ac4-a344-f2b0ba0939b7","added_by":"auto","created_at":"2024-04-17 03:15:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1060919,"visible":true,"origin":"","legend":"","description":"","filename":"Version2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4277216/v1_covered_f82fcad6-fe2a-4638-9b59-abcad505d652.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eAn on-chip programmable diffractive deep neural network based on Sb\u003c/strong\u003e\u003csub\u003e\u003cstrong\u003e2\u003c/strong\u003e\u003c/sub\u003e\u003cstrong\u003eSe\u003c/strong\u003e\u003csub\u003e\u003cstrong\u003e3\u003c/strong\u003e\u003c/sub\u003e\u003cstrong\u003e-incorporated silicon metalines\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"136a1778-9f7a-42f5-8ebe-c8c7af368167","identifier":"10.13039/501100018981","name":"Iran Science Elites Federation","awardNumber":"401478","order_by":0}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Sharif University of Technology","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Programmable optical neural network, Diffractive deep neural network, Sb2Se3-incorporated silicon metalines","lastPublishedDoi":"10.21203/rs.3.rs-4277216/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4277216/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eArtificial intelligence is a technology for simulating and extending human intelligence and has rapidly altered many aspects of modern society. Optical processors, which compute with photons instead of electrons, can fundamentally accelerate the development of artificial intelligence by offering substantially improved computing performance. Photonic approaches for demonstrating artificial neural networks as one of the most widely used frameworks in artificial intelligence, show extraordinary potential to achieve brain-inspired information processing at the speed of light. Recently, all-optical diffractive deep neural networks have been created that are based on passive structures and can perform complicated functions designed by computer-based neural networks. However, existing passive diffractive deep neural networks are not reconfigurable and once is fabricated, its function is fixed. This work reports an on-chip programmable deep diffractive neural network (OPD\u003csup\u003e2\u003c/sup\u003eNN), in which the optical neurons are built with Sb\u003csub\u003e2\u003c/sub\u003eSe\u003csub\u003e3\u003c/sub\u003e phase change material, making the network reconfigurable and non-volatile. Using numerical simulations, the performance of the OPD\u003csup\u003e2\u003c/sup\u003eNN is benchmarked on two machine learning tasks that are learning a multifunctional (AND-OR-NOT) logic gate and classification of images of handwritten digits from the MNIST dataset and the obtained results are validated using FDTD simulations by a commercially available full-wave electromagnetic solver. Both numerical and FDTD simulations indicate that a five-hidden-layer OPD\u003csup\u003e2\u003c/sup\u003eNN with a footprint of 30μmx150μm can appropriately handle (AND-OR-NOT) logic functions. For handwritten digits (0-1-2-3) classification, a three-hidden-layer OPD\u003csup\u003e2\u003c/sup\u003eNN with a footprint of 60μmx105μm can achieve numerical testing accuracy of 91.5% on the test dataset and the FDTD verification results show 73% matching with numerical testing results.\u003c/p\u003e","manuscriptTitle":"An on-chip programmable diffractive deep neural network based on Sb2Se3-incorporated silicon metalines","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-17 03:07:16","doi":"10.21203/rs.3.rs-4277216/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d317235e-fc02-48f5-b560-80cbfa08a6a8","owner":[],"postedDate":"April 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-17T03:07:16+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-17 03:07:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4277216","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4277216","identity":"rs-4277216","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}