Spintronics for image recognition: performance benchmarking via ultrafast data-driven simulations

Spintronics for image recognition: performance benchmarking via ultrafast data-driven simulations | 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 Article Spintronics for image recognition: performance benchmarking via ultrafast data-driven simulations Anatole Moureaux, Chloé Chopin, Simon de Wergifosse, Laurent Jacques, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3931380/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 We present a demonstration of image classification using an echo-state network (ESN) relying on a single simulated spintronic nanostructure known as the vortex-based spin-torque oscillator (STVO) delayed in time. We employ an ultrafast data-driven simulation framework called the data-driven Thiele equation approach (DD-TEA) to simulate the STVO dynamics. This allows us to avoid the challenges associated with repeated experimental manipulation of such a nanostructured system. We showcase the versatility of our solution by successfully applying it to solve classification challenges with the MNIST, EMNIST-letters and Fashion MNIST datasets. Through our simulations, we determine that within an ESN with numerous learnable parameters the results obtained using the STVO dynamics as an activation function are comparable to the ones obtained with other conventional nonlinear activation functions like the reLU and the sigmoid. While achieving state-of-the-art accuracy levels on the MNIST dataset, our model’s performance on EMNIST-letters and Fashion MNIST is lower due to the relative simplicity of the system architecture and the increased complexity of the tasks. We expect that the DD-TEA framework will enable the exploration of deeper architectures, ultimately leading to improved classification accuracy. Physical sciences/Materials science/Condensed-matter physics/Spintronics Physical sciences/Mathematics and computing/Computational science Physical sciences/Nanoscience and technology/Nanoscale devices/Magnetic devices Full Text Additional Declarations There is NO Competing Interest. 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-3931380","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":271353082,"identity":"22d9483b-033f-4882-8d4c-e8171a9ec634","order_by":0,"name":"Anatole Moureaux","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0003-2969-2154","institution":"Université catholique de Louvain","correspondingAuthor":true,"prefix":"","firstName":"Anatole","middleName":"","lastName":"Moureaux","suffix":""},{"id":271353083,"identity":"254422ed-da36-42d5-8b35-210fd7940749","order_by":1,"name":"Chloé Chopin","email":"","orcid":"","institution":"Université Grenoble Alpes","correspondingAuthor":false,"prefix":"","firstName":"Chloé","middleName":"","lastName":"Chopin","suffix":""},{"id":271353084,"identity":"71f70e5c-e79d-4441-831b-2ee9e681fcbb","order_by":2,"name":"Simon de Wergifosse","email":"","orcid":"","institution":"Université catholique de Louvain","correspondingAuthor":false,"prefix":"","firstName":"Simon","middleName":"","lastName":"de Wergifosse","suffix":""},{"id":271353085,"identity":"b63d75b7-c52f-4842-9184-b8355ed6d81d","order_by":3,"name":"Laurent Jacques","email":"","orcid":"","institution":"Université catholique de Louvain","correspondingAuthor":false,"prefix":"","firstName":"Laurent","middleName":"","lastName":"Jacques","suffix":""},{"id":271353086,"identity":"a0d55ad5-c4f0-498e-ac4e-2beeb4821ea0","order_by":4,"name":"Flavio Abreu Araujo","email":"","orcid":"https://orcid.org/0000-0001-7157-3197","institution":"Université catholique de Louvain","correspondingAuthor":false,"prefix":"","firstName":"Flavio","middleName":"Abreu","lastName":"Araujo","suffix":""}],"badges":[],"createdAt":"2024-02-05 15:40:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3931380/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3931380/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":53746588,"identity":"29f883a5-b97c-4252-b6b7-cf0fff6af93d","added_by":"auto","created_at":"2024-03-29 17:53:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":722989,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3931380/v1_covered_a0853d77-7303-449f-9ff2-fe29232b453f.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Spintronics for image recognition: performance benchmarking via ultrafast data-driven simulations","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","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":"","lastPublishedDoi":"10.21203/rs.3.rs-3931380/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3931380/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We present a demonstration of image classification using an echo-state network (ESN) relying on a single simulated spintronic nanostructure known as the vortex-based spin-torque oscillator (STVO) delayed in time. We employ an ultrafast data-driven simulation framework called the data-driven Thiele equation approach (DD-TEA) to simulate the STVO dynamics. This allows us to avoid the challenges associated with repeated experimental manipulation of such a nanostructured system. We showcase the versatility of our solution by successfully applying it to solve classification challenges with the MNIST, EMNIST-letters and Fashion MNIST datasets. Through our simulations, we determine that within an ESN with numerous learnable parameters the results obtained using the STVO dynamics as an activation function are comparable to the ones obtained with other conventional nonlinear activation functions like the reLU and the sigmoid. While achieving state-of-the-art accuracy levels on the MNIST dataset, our model’s performance on\r\nEMNIST-letters and Fashion MNIST is lower due to the relative simplicity of the system architecture and the increased\r\ncomplexity of the tasks. We expect that the DD-TEA framework will enable the exploration of deeper architectures, ultimately leading to improved classification accuracy.","manuscriptTitle":"Spintronics for image recognition: performance benchmarking via ultrafast data-driven simulations","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-19 03:04:59","doi":"10.21203/rs.3.rs-3931380/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":"daff1416-50f5-4737-ba8f-8d3be6cd1bf2","owner":[],"postedDate":"February 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":28605198,"name":"Physical sciences/Materials science/Condensed-matter physics/Spintronics"},{"id":28605199,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":28605200,"name":"Physical sciences/Nanoscience and technology/Nanoscale devices/Magnetic devices"}],"tags":[],"updatedAt":"2024-03-29T17:45:39+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-19 03:04:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3931380","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3931380","identity":"rs-3931380","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}