Scalable and Energy-Efficient Peierls Transition Neuron for Monolithic Integrated Neural Network

Scalable and Energy-Efficient Peierls Transition Neuron for Monolithic Integrated Neural Network | 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 Scalable and Energy-Efficient Peierls Transition Neuron for Monolithic Integrated Neural Network Daeseok Lee, Seojin Cho, Yuna Kim, Minsu Kang, Hyejin Kim, Yunsur Kim, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7178914/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 While in-memory computing offers a promising approach to overcoming the limitations of the traditional von Neumann architecture, implementing an activation function, a critical component of neural networks, still requires substantial energy and area consumption when using conventional analog or digital circuitry. In this study, we introduce a two-terminal niobium-dioxide-based Peierls transition neuron (Peierls-neuron) that enables direct device-level implementation of the activation function. Through monolithic three-dimensional(3D) vertical integration of Peierls-neurons with synaptic devices, a highly compact neural network architecture is achieved featuring minimal interconnect overhead and maximum array density. A simple tuning method using a parallel resistor allows seamless compatibility with a broad range of synaptic conductance levels, thereby eliminating the need for additional peripheral circuits. Our integrated architecture achieves over 10 4 times area reduction and up to 183.7 times energy savings compared with conventional activation function circuits. These results demonstrate a highly scalable and energy-efficient solution for the hardware implementation of neural network. Physical sciences/Materials science/Materials for devices/Electronic devices Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Physics/Electronics, photonics and device physics/Electronic and spintronic devices In-memory computing Peierls transition NbO2 neuron device 3D monolithic integration ReLU implementation Neuromorphic hardware Full Text Additional Declarations There is NO Competing Interest. Supplementary Files NbOxNaturetemplatesupplementary.pdf Supplementary information 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-7178914","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":498424587,"identity":"11c33df9-e757-4886-b1a7-35cf00e5956d","order_by":0,"name":"Daeseok Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArElEQVRIiWNgGAWjYBACPiCWYKhIAHMYG4jRwgbWcoZkLYxtJGlhbz548+e8tMQG9sMPGGfuIUYLz7Fka95tOYkNPGkGjBueEaNFIsdMmnFbRW4DQw4D44MDxGiRf/9N8uccoBb+N8RqkeBhk+BtyMltkADasoEoLTxpxtY8x9Lq2ySeGRycQYwWfvbDD2/+qEk25udPfviwhxgtCOuAmCQNo2AUjIJRMArwAADh5zLU4i7YhgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-4548-2387","institution":"Kwangwoon University","correspondingAuthor":true,"prefix":"","firstName":"Daeseok","middleName":"","lastName":"Lee","suffix":""},{"id":498424588,"identity":"4737c66a-e8f8-4480-853b-8a18d5c302de","order_by":1,"name":"Seojin Cho","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Seojin","middleName":"","lastName":"Cho","suffix":""},{"id":498424589,"identity":"99d194fb-3181-4f04-856b-9232b578ad13","order_by":2,"name":"Yuna Kim","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Yuna","middleName":"","lastName":"Kim","suffix":""},{"id":498424590,"identity":"4a95e02f-2545-4e7b-b74d-6078d8c9cf77","order_by":3,"name":"Minsu Kang","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Minsu","middleName":"","lastName":"Kang","suffix":""},{"id":498424591,"identity":"6fe7c0df-3035-44d5-a104-cd87d3ae7368","order_by":4,"name":"Hyejin Kim","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Hyejin","middleName":"","lastName":"Kim","suffix":""},{"id":498424592,"identity":"c1973380-4809-47c9-84d4-1c39d5998ecb","order_by":5,"name":"Yunsur Kim","email":"","orcid":"","institution":"Kyungpook National University","correspondingAuthor":false,"prefix":"","firstName":"Yunsur","middleName":"","lastName":"Kim","suffix":""},{"id":498424593,"identity":"bc03c8e1-5f5e-42ed-b650-fc832e931073","order_by":6,"name":"Chuljun Lee","email":"","orcid":"","institution":"Pohang University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Chuljun","middleName":"","lastName":"Lee","suffix":""},{"id":498424594,"identity":"562c5086-bd2b-4ec3-aef4-6c9baae9b52b","order_by":7,"name":"Jiyong Woo","email":"","orcid":"","institution":"Kyungpook National University","correspondingAuthor":false,"prefix":"","firstName":"Jiyong","middleName":"","lastName":"Woo","suffix":""}],"badges":[],"createdAt":"2025-07-21 15:10:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7178914/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7178914/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90976501,"identity":"719797ff-0b8a-4710-b3bd-9481a2afcca7","added_by":"auto","created_at":"2025-09-10 08:39:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2261912,"visible":true,"origin":"","legend":"Article File","description":"","filename":"NbOxNaturetemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7178914/v1_covered_ee45cf88-576b-4fae-8ef4-e479cfa7384d.pdf"},{"id":88872817,"identity":"681b7baf-4175-4856-8682-33d46b483aea","added_by":"auto","created_at":"2025-08-12 09:33:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1556403,"visible":true,"origin":"","legend":"Supplementary information","description":"","filename":"NbOxNaturetemplatesupplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7178914/v1/ee581f584dd98ec8149f1ca0.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Scalable and Energy-Efficient Peierls Transition Neuron for Monolithic Integrated Neural Network","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":"In-memory computing, Peierls transition, NbO2 neuron device, 3D monolithic integration, ReLU implementation, Neuromorphic hardware","lastPublishedDoi":"10.21203/rs.3.rs-7178914/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7178914/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"While in-memory computing offers a promising approach to overcoming the limitations of the traditional von Neumann architecture, implementing an activation function, a critical component of neural networks, still requires substantial energy and area consumption when using conventional analog or digital circuitry. In this study, we introduce a two-terminal niobium-dioxide-based Peierls transition neuron (Peierls-neuron) that enables direct device-level implementation of the activation function. Through monolithic three-dimensional(3D) vertical integration of Peierls-neurons with synaptic devices, a highly compact neural network architecture is achieved featuring minimal interconnect overhead and maximum array density. A simple tuning method using a parallel resistor allows seamless compatibility with a broad range of synaptic conductance levels, thereby eliminating the need for additional peripheral circuits. Our integrated architecture achieves over 10\u003csup\u003e4\u003c/sup\u003e times area reduction and up to 183.7 times energy savings compared with conventional activation function circuits. These results demonstrate a highly scalable and energy-efficient solution for the hardware implementation of neural network.","manuscriptTitle":"Scalable and Energy-Efficient Peierls Transition Neuron for Monolithic Integrated Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-12 09:33:41","doi":"10.21203/rs.3.rs-7178914/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":"650ea14f-487e-4212-a0c9-ecc022228c08","owner":[],"postedDate":"August 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52935937,"name":"Physical sciences/Materials science/Materials for devices/Electronic devices"},{"id":52935938,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":52935939,"name":"Physical sciences/Physics/Electronics, photonics and device physics/Electronic and spintronic devices"}],"tags":[],"updatedAt":"2025-09-10T08:31:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-12 09:33:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7178914","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7178914","identity":"rs-7178914","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}