Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks

Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks | 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 Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks MD Azizul Hakim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8117650/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 neural networks achieve strong performance on benchmark tasks but remain fundamentally brittle under perturbations, limiting their deployment in real-world settings. In contrast, biological nervous systems sustain reliable function across decades through homeostatic regulation coordinated across multiple temporal scales. Inspired by this principle, this presents Multi-Scale Temporal Homeostasis (MSTH), a biologically grounded framework that integrates ultra-fast (5-ms), fast (2-s), medium (5-min) and slow (1-hrs) regulation into artificial networks. MSTH implements the cross-scale coordination system for artificial neural networks, providing a unified temporal hierarchy that moves beyond superficial biomimicry. The cross-scale coordination enhances computational efficiency through evolutionary-refined optimization mechanisms. Experiments across molecular, graph and image classification benchmarks show that MSTH consistently improves accuracy, eliminates catastrophic failures and enhances recovery from perturbations. Moreover, MSTH outperforms both single-scale bio-inspired models and established state-of-the-art methods, demonstrating generality across diverse domains. These findings establish cross-scale temporal coordination as a core principle for stabilizing artificial neural systems, positioning MSTH as a foundation for building robust, resilient and biologically faithful intelligence. 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-8117650","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":545275654,"identity":"bc57c8d5-5e7f-41f7-b927-d4f8d06678a3","order_by":0,"name":"MD Azizul Hakim","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0008-7738-6200","institution":"Bangladesh Sweden Polytechnic Institute","correspondingAuthor":true,"prefix":"","firstName":"MD","middleName":"Azizul","lastName":"Hakim","suffix":""}],"badges":[],"createdAt":"2025-11-14 18:45:12","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-8117650/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8117650/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96246376,"identity":"fb64742a-4a8c-4a4f-809e-33e4d748f0e8","added_by":"auto","created_at":"2025-11-19 07:25:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":14097149,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8117650/v1_covered_0ca1117c-3aed-453c-bf81-bd4d55260512.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eMulti-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Bangladesh Sweden Polytechic Institute","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-8117650/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8117650/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eArtificial neural networks achieve strong performance on benchmark tasks but remain fundamentally brittle under perturbations, limiting their deployment in real-world settings. In contrast, biological nervous systems sustain reliable function across decades through homeostatic regulation coordinated across multiple temporal scales. Inspired by this principle, this presents Multi-Scale Temporal Homeostasis (MSTH), a biologically grounded framework that integrates ultra-fast (5-ms), fast (2-s), medium (5-min) and slow (1-hrs) regulation into artificial networks. MSTH implements the cross-scale coordination system for artificial neural networks, providing a unified temporal hierarchy that moves beyond superficial biomimicry. The cross-scale coordination enhances computational efficiency through evolutionary-refined optimization mechanisms. Experiments across molecular, graph and image classification benchmarks show that MSTH consistently improves accuracy, eliminates catastrophic failures and enhances recovery from perturbations. Moreover, MSTH outperforms both single-scale bio-inspired models and established state-of-the-art methods, demonstrating generality across diverse domains. These findings establish cross-scale temporal coordination as a core principle for stabilizing artificial neural systems, positioning MSTH as a foundation for building robust, resilient and biologically faithful intelligence.\u003c/p\u003e","manuscriptTitle":"Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-17 07:26:18","doi":"10.21203/rs.3.rs-8117650/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":"ce8e3bba-b370-4c41-963f-dde78acc2b0d","owner":[],"postedDate":"November 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-17T07:26:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-17 07:26:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8117650","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8117650","identity":"rs-8117650","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}