Reshaping Reservoirs with Hebbian Plasticity:Unsupervised Adaptation that Works

Reshaping Reservoirs with Hebbian Plasticity:Unsupervised Adaptation that Works | 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 Reshaping Reservoirs with Hebbian Plasticity:Unsupervised Adaptation that Works Tanguy Cazalets, Joni Dambre This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6759166/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 Dec, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract Reservoir Computing (RC) is a lightweight way to model time-dependent data, yet its reliance on static, randomly initialized network architectures often limits performance on challenging real-world problems. We introduce Hebbian Architecture Generation (HAG), an unsupervised rule that grows connections between neurons that frequently activate together—embodying the biological maxim “neurons that fire together wire together.” Starting from an almost empty reservoir, HAG progressively sculpts a task-specific wiring. Across a diverse set of classification and forecasting tasks reservoirs reshaped by HAG are consistently more accurate than traditional Echo State Networks and than reservoirs tuned with popular plasticity rules such as Intrinsic Plasticity or anti-Oja learning. In other words, letting the network rewire itself from data turns a once-static RC model into a flexible, high-performance learner without a single gradient step. By coupling the efficiency of RC with the adaptability of Hebbian plasticity, HAG moves reservoir computing closer to its biological inspiration and shows that structural self-organisation is a practical route to robust, task-aware processing of real-world time-series data. Physical sciences/Mathematics and computing/Computer science Biological sciences/Computational biology and bioinformatics/Computational neuroscience/Learning algorithms Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Computational models Bio-inspired Hebbian learning Reservoir Computing Dimensionality expansion Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 13 Dec, 2025 Read the published version in Nature Communications → 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-6759166","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":465901973,"identity":"e1706e78-4ece-4613-8960-e6c106a248c1","order_by":0,"name":"Tanguy Cazalets","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEUlEQVRIie2OIWvDQBTHXygk5rbYU8lXuHAQs8K+ys00JhtToyqrmirUdjC3L9B+gwsPMpPtbERFoRCziMyMiopdaEXErqNu0PuJx/vD+/H+ABbLP8eRegSHII1npB8kCOCH7QTlZvKXcu294+fFE4T+DNfya5slC/VabFpYBSaFkLvRlVaiuSxYPhd4u6jqhEmoublYGnOtCMgnDImQWiljKgH3DX9T/GavhOi1uBNZwir13SmPRoWmfNMprCAMQQwEU1O3U4SxWNXEzssHjZYluc+nI4yeKzemJasj0xdvlvK2eRiGgXpbrrfDLLxUWNPxeBWavmhc6ri0l2lXiR0RAAYt7PrZl0fPLRaL5fz4ASDCYQSYQzgJAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-5614-5573","institution":"Ghent University","correspondingAuthor":true,"prefix":"","firstName":"Tanguy","middleName":"","lastName":"Cazalets","suffix":""},{"id":465901974,"identity":"afb6115e-0264-464b-b544-e8cc92e3f7f8","order_by":1,"name":"Joni Dambre","email":"","orcid":"","institution":"Ghent University","correspondingAuthor":false,"prefix":"","firstName":"Joni","middleName":"","lastName":"Dambre","suffix":""}],"badges":[],"createdAt":"2025-05-27 11:56:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6759166/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6759166/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-67137-1","type":"published","date":"2025-12-13T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100213859,"identity":"80a61997-4c49-4631-ad5f-e9897400ab5d","added_by":"auto","created_at":"2026-01-14 08:10:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":21505861,"visible":true,"origin":"","legend":"Article File","description":"","filename":"ReshapingReservoirs.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6759166/v1_covered_a6f164ca-567f-44e5-b0c8-561e31e33e1f.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Reshaping Reservoirs with Hebbian Plasticity:Unsupervised Adaptation that Works","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"Bio-inspired, Hebbian learning, Reservoir Computing, Dimensionality expansion","lastPublishedDoi":"10.21203/rs.3.rs-6759166/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6759166/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Reservoir Computing (RC) is a lightweight way to model time-dependent data, yet its reliance on static, randomly initialized network architectures often limits performance on challenging real-world problems.\r\n\r\nWe introduce Hebbian Architecture Generation (HAG), an unsupervised rule that grows connections between neurons that frequently activate together—embodying the biological maxim “neurons that fire together wire together.” Starting from an almost empty reservoir, HAG progressively sculpts a task-specific wiring. Across a diverse set of classification and forecasting tasks reservoirs reshaped by HAG are consistently more accurate than traditional Echo State Networks and than reservoirs tuned with popular plasticity rules such as Intrinsic Plasticity or anti-Oja learning. In other words, letting the network rewire itself from data turns a once-static RC model into a flexible, high-performance learner without a single gradient step.\r\n\r\nBy coupling the efficiency of RC with the adaptability of Hebbian plasticity, HAG moves reservoir computing closer to its biological inspiration and shows that structural self-organisation is a practical route to robust, task-aware processing of real-world time-series data.","manuscriptTitle":"Reshaping Reservoirs with Hebbian Plasticity:Unsupervised Adaptation that Works","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-04 08:39:33","doi":"10.21203/rs.3.rs-6759166/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"aa72ebca-3085-452a-892e-cc686b23f6d0","owner":[],"postedDate":"June 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49462176,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":49462177,"name":"Biological sciences/Computational biology and bioinformatics/Computational neuroscience/Learning algorithms"},{"id":49462178,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":49462179,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"}],"tags":[],"updatedAt":"2026-01-14T08:09:20+00:00","versionOfRecord":{"articleIdentity":"rs-6759166","link":"https://doi.org/10.1038/s41467-025-67137-1","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-12-13 05:00:00","publishedOnDateReadable":"December 13th, 2025"},"versionCreatedAt":"2025-06-04 08:39:33","video":"","vorDoi":"10.1038/s41467-025-67137-1","vorDoiUrl":"https://doi.org/10.1038/s41467-025-67137-1","workflowStages":[]},"version":"v1","identity":"rs-6759166","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6759166","identity":"rs-6759166","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}