Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing

Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing | 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 Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing Can Li, Zhu Wang, Song Wang, Zhiyuan Du, Ruibin Mao, Yu Xiao, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7141224/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract The demand for edge artificial intelligence to process event-based, complex data calls for hardware beyond conventional digital, von-Neumann architectures. Neuromorphic computing, using spiking neural networks (SNNs) with emerging memristors, is a promising solution, but existing systems often discard temporal information, demonstrate non-competitive accuracy, or rely on neuron designs with large capacitors that limit the scalability and processing speed. Here we experimentally demonstrate a fully integrated memristive SNN with a 128×24 memristor array integrated on a CMOS chip and custom-designed analog neurons, achieving high-speed, energy-efficient event-driven processing of accelerated spatiotemporal spike signals with high computational fidelity. This is achieved through a proportional time-scaling property of the analog neurons, which allows them to use only compact on-chip capacitors and train directly on the spatiotemporal data without special encoding by backpropagation through surrogate gradient, thus overcoming the speed, scalability and accuracy limitations of previous designs. We experimentally validated our hardware using the DVS128 Gesture dataset, accelerating each sample 50,000-fold to a 30 µs duration. The system achieves an experimental accuracy of 93.06% with a measured energy efficiency of 101.05 TSOPS/W. We project significant future efficiency gains by leveraging picosecond-width spikes and advanced fabrication nodes. By decoupling the hardware’s operational timescale from the data’s natural timescale, this work establishes a viable pathway for developing neuromorphic processors capable of high-throughput analysis, critical for rapid-response edge computing applications like high-speed analysis of buffered sensor data or ultra-fast in-sensor machine vision. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Nanoscience and technology/Nanoscale devices/Electronic devices Full Text Additional Declarations Yes there is potential Competing Interest. C.L., Z.W., S.W., and H.K.-H.S. are named inventors on patent applications US2024/0202513A1 and CN118211616A, which cover aspects of the custom-designed analog spiking neuron circuits reported in this study. These patents are held by The University of Hong Kong. The remaining authors declare no competing interests. Supplementary Files 20250705SRMSNNSI.pdf Supplementary Information Cite Share Download PDF Status: Under Review 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-7141224","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":510206018,"identity":"f2637c81-907e-4cdc-ac4d-12050b6ca1bf","order_by":0,"name":"Can Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAlElEQVRIiWNgGAWjYHACxgMfGxIYGCTYSNBzcCbJWg7zkqSFv/3sgcO2O9ISG6TbEojTInEmL+Fw7pmcxAaZYweI02LAkGNwOLetIrFBIr2BSC38bwwOW5KmRQJoC2Mb0GESaUQ6TOLGG4ODvW1pxm0SaQnEaeHvzzF88LMtWbZfIs2AOC1wQEpEjoJRMApGwSggBAAIki2ZhBHEQgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-3795-2008","institution":"The University of Hong Kong","correspondingAuthor":true,"prefix":"","firstName":"Can","middleName":"","lastName":"Li","suffix":""},{"id":510206019,"identity":"6e4357f6-495f-4d6d-b09b-506c36ff9776","order_by":1,"name":"Zhu Wang","email":"","orcid":"https://orcid.org/0000-0002-3859-1008","institution":"The University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Zhu","middleName":"","lastName":"Wang","suffix":""},{"id":510206020,"identity":"3c43d414-b8f6-4450-aee1-d080e6e7c49c","order_by":2,"name":"Song Wang","email":"","orcid":"https://orcid.org/0000-0002-1813-5865","institution":"The University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Song","middleName":"","lastName":"Wang","suffix":""},{"id":510206021,"identity":"0aa01865-b99a-44c4-aa0b-1ca2495d11c7","order_by":3,"name":"Zhiyuan Du","email":"","orcid":"","institution":"University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Zhiyuan","middleName":"","lastName":"Du","suffix":""},{"id":510206022,"identity":"74b42c21-60e9-4a0c-a91f-9c98495a13ce","order_by":4,"name":"Ruibin Mao","email":"","orcid":"https://orcid.org/0000-0001-6085-0486","institution":"University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Ruibin","middleName":"","lastName":"Mao","suffix":""},{"id":510206023,"identity":"7da21a64-acd4-40b5-af53-471cf36673df","order_by":5,"name":"Yu Xiao","email":"","orcid":"https://orcid.org/0009-0009-2292-6588","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Xiao","suffix":""},{"id":510206024,"identity":"06e3d720-f319-47aa-9515-b635f7eb3732","order_by":6,"name":"Hayden So","email":"","orcid":"https://orcid.org/0000-0002-6514-0237","institution":"The University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Hayden","middleName":"","lastName":"So","suffix":""},{"id":510206025,"identity":"4351265f-c3f4-46f5-afd2-cd1d899df799","order_by":7,"name":"Peng Lin","email":"","orcid":"https://orcid.org/0000-0002-0679-8063","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Lin","suffix":""}],"badges":[],"createdAt":"2025-07-16 14:50:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7141224/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7141224/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90616807,"identity":"44ab5139-a11f-4fdc-ac20-a6af8c9dd23b","added_by":"auto","created_at":"2025-09-04 18:50:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4374783,"visible":true,"origin":"","legend":"Article File","description":"","filename":"20250716SRMSNNMaintext.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7141224/v1_covered_937674cd-5d75-4c7a-95bf-56d754757921.pdf"},{"id":90616636,"identity":"d2643e97-7ee4-44f2-87be-e29bf89e768a","added_by":"auto","created_at":"2025-09-04 18:42:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2149306,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"20250705SRMSNNSI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7141224/v1/a0a90aad4cd596343527f35a.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nC.L., Z.W., S.W., and H.K.-H.S. are named inventors on patent applications US2024/0202513A1 and CN118211616A, which cover aspects of the custom-designed analog spiking neuron circuits reported in this study. These patents are held by The University of Hong Kong. The remaining authors declare no competing interests.","formattedTitle":"Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7141224/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7141224/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The demand for edge artificial intelligence to process event-based, complex data calls for hardware beyond conventional digital, von-Neumann architectures. Neuromorphic computing, using spiking neural networks (SNNs) with emerging memristors, is a promising solution, but existing systems often discard temporal information, demonstrate non-competitive accuracy, or rely on neuron designs with large capacitors that limit the scalability and processing speed. Here we experimentally demonstrate a fully integrated memristive SNN with a 128×24 memristor array integrated on a CMOS chip and custom-designed analog neurons, achieving high-speed, energy-efficient event-driven processing of accelerated spatiotemporal spike signals with high computational fidelity. This is achieved through a proportional time-scaling property of the analog neurons, which allows them to use only compact on-chip capacitors and train directly on the spatiotemporal data without special encoding by backpropagation through surrogate gradient, thus overcoming the speed, scalability and accuracy limitations of previous designs. We experimentally validated our hardware using the DVS128 Gesture dataset, accelerating each sample 50,000-fold to a 30 µs duration. The system achieves an experimental accuracy of 93.06% with a measured energy efficiency of 101.05 TSOPS/W. We project significant future efficiency gains by leveraging picosecond-width spikes and advanced fabrication nodes. By decoupling the hardware’s operational timescale from the data’s natural timescale, this work establishes a viable pathway for developing neuromorphic processors capable of high-throughput analysis, critical for rapid-response edge computing applications like high-speed analysis of buffered sensor data or ultra-fast in-sensor machine vision.","manuscriptTitle":"Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-04 18:42:16","doi":"10.21203/rs.3.rs-7141224/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-electronics","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natelectron","sideBox":"Learn more about [Nature Electronics](http://www.nature.com/natelectron/)","snPcode":"","submissionUrl":"","title":"Nature Electronics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"0a45fac0-4538-444b-931d-fe64f67737bf","owner":[],"postedDate":"September 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":54192605,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":54192606,"name":"Physical sciences/Nanoscience and technology/Nanoscale devices/Electronic devices"}],"tags":[],"updatedAt":"2026-04-08T11:31:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-04 18:42:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7141224","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7141224","identity":"rs-7141224","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}