Optimized Spiking Neural Network Architecture for Fashion MNIST Classification: A Comparative Study with Convolutional Neural Networks

Optimized Spiking Neural Network Architecture for Fashion MNIST Classification: A Comparative Study with Convolutional 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 Article Optimized Spiking Neural Network Architecture for Fashion MNIST Classification: A Comparative Study with Convolutional Neural Networks Chiang Liang Kok, Guangming Ren, Tee Hui Teo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6265682/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 The Spiking Neural Network (SNN) is an event-driven and energy-efficient system inspired by biological neurons. It began to appeal too much in the past few years. The optimized SNN architecture holds a new record for Fashion MNIST classification and has structural innovations to enhance performance. Comparison with Convolutional Neural Networks (CNNs) Costs of operation and image processing points to a result in favour of SNNs. Experimental results show that the optimized SNN obtains competitive classification accuracy with significantly lower energy consumption than previous efforts, making it ideal for anything from real-time to yearlong power efficiency applications. Physical sciences/Engineering/Biomedical engineering Physical sciences/Engineering/Electrical and electronic engineering Full Text Additional Declarations No competing interests reported. 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-6265682","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":433891645,"identity":"ebddb612-ae85-4a0e-b8b6-7fb18b13779f","order_by":0,"name":"Chiang Liang Kok","email":"data:image/png;base64,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","orcid":"","institution":"The University of Newcastle","correspondingAuthor":true,"prefix":"","firstName":"Chiang","middleName":"Liang","lastName":"Kok","suffix":""},{"id":433891646,"identity":"173e6e0f-a450-4b97-ab4f-63a96437f7a2","order_by":1,"name":"Guangming Ren","email":"","orcid":"","institution":"The University of Newcastle","correspondingAuthor":false,"prefix":"","firstName":"Guangming","middleName":"","lastName":"Ren","suffix":""},{"id":433891647,"identity":"bd2547d3-673d-4016-b40d-bbda1ad3e557","order_by":2,"name":"Tee Hui Teo","email":"","orcid":"","institution":"The Singapore University of Technology and Design","correspondingAuthor":false,"prefix":"","firstName":"Tee","middleName":"Hui","lastName":"Teo","suffix":""}],"badges":[],"createdAt":"2025-03-20 03:23:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6265682/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6265682/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88323090,"identity":"00fa08b1-286c-491c-8b62-5d84915b05ae","added_by":"auto","created_at":"2025-08-05 09:17:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":721068,"visible":true,"origin":"","legend":"","description":"","filename":"OptimizedSpikingNeuralNetworkArchitecturefor.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6265682/v1_covered_84bb2f09-aeb2-48f6-8351-d783ba2cbb38.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimized Spiking Neural Network Architecture for Fashion MNIST Classification: A Comparative Study with Convolutional Neural Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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-6265682/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6265682/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The Spiking Neural Network (SNN) is an event-driven and energy-efficient system inspired by biological neurons. It began to appeal too much in the past few years. The optimized SNN architecture holds a new record for Fashion MNIST classification and has structural innovations to enhance performance. Comparison with Convolutional Neural Networks (CNNs) Costs of operation and image processing points to a result in favour of SNNs. Experimental results show that the optimized SNN obtains competitive classification accuracy with significantly lower energy consumption than previous efforts, making it ideal for anything from real-time to yearlong power efficiency applications.","manuscriptTitle":"Optimized Spiking Neural Network Architecture for Fashion MNIST Classification: A Comparative Study with Convolutional Neural Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-02 06:51:54","doi":"10.21203/rs.3.rs-6265682/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":"086c0922-5b91-4beb-98e3-b707c7f39a76","owner":[],"postedDate":"April 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46202136,"name":"Physical sciences/Engineering/Biomedical engineering"},{"id":46202137,"name":"Physical sciences/Engineering/Electrical and electronic engineering"}],"tags":[],"updatedAt":"2025-08-05T09:09:10+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-02 06:51:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6265682","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6265682","identity":"rs-6265682","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}