Comparing Kolmogorov-Arnold Network Autoencoders versus MLP Autoencoders for the analysis of biomedical data

Comparing Kolmogorov-Arnold Network Autoencoders versus MLP Autoencoders for the analysis of biomedical data | 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 Comparing Kolmogorov-Arnold Network Autoencoders versus MLP Autoencoders for the analysis of biomedical data Ugo Lomoio, Pierangelo Veltri, Pietro Hiram Guzzi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7223313/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 Current research extensively utilises deep learning architectures like Multi-Layer Perceptrons and Convolutional Neural Networks. Topologi- cally, these can be viewed as graphs where node functions are learned, and fixed edges facilitate information flow. A novel architecture, Kolmogorov- Arnold Networks, has been proposed, demonstrating improved performance across various applications by incorporating learnable activation functions on network edges. Ongoing research aims to enhance KANs through fea- tures such as dropout regularisation, Autoencoders, model benchmarking, and the development of KAN Convolutional Networks for matrix convo- lution. This study compares the performance of standard Autoencoders with their Kolmogorov-Arnold counterparts, which possess an equivalent or smaller parameter count, using cardiologic performance signals as input. Specifically, some classic AE tasks such as reconstruction, , denoising, and inpainting, were evaluated on the AbnormalHeartbeat dataset, which comprises audio signals recorded via stethoscope. Bioinformatics Medical Informatics 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-7223313","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":491355575,"identity":"a62bc85e-8c8b-4d1a-bd79-32e79466874c","order_by":0,"name":"Ugo Lomoio","email":"","orcid":"","institution":"University of Catanzaro","correspondingAuthor":false,"prefix":"","firstName":"Ugo","middleName":"","lastName":"Lomoio","suffix":""},{"id":491355576,"identity":"0aef31d4-0464-4377-86ba-e27b03d7d2c7","order_by":1,"name":"Pierangelo Veltri","email":"","orcid":"","institution":"UNICAL","correspondingAuthor":false,"prefix":"","firstName":"Pierangelo","middleName":"","lastName":"Veltri","suffix":""},{"id":491355618,"identity":"6160b82d-83b9-43b7-85ce-d6b1c01f8189","order_by":2,"name":"Pietro Hiram Guzzi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYBACAwhpw8DAjOASpSUNpoUIPVAlh9H4+IA5/xrjjz8KziduZ2d+/IGh4A9hLZYz3hgYSBjcTtzZzAZ0FVEOu3HGIMEAqGXDYR6GBKK1HEgwOAfWcoA4Led7DBsOGBwAaWFsINIWtmLGBoNk4w2H2YwZEgyMibHl8OaPP/7YyW44f/jxhw9/5AhrYZBIQOIk4FCECvgPEKVsFIyCUTAKRjIAALx3OC2pERg3AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-5542-2997","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Pietro","middleName":"Hiram","lastName":"Guzzi","suffix":""}],"badges":[],"createdAt":"2025-07-26 22:02:53","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7223313/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7223313/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87818192,"identity":"302920a0-2028-409c-a802-ccb193e11cf2","added_by":"auto","created_at":"2025-07-29 10:30:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8401003,"visible":true,"origin":"","legend":"","description":"","filename":"2025KANBIOMED2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7223313/v1_covered_69773933-1738-4469-93f5-86bf5b439d19.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eComparing Kolmogorov-Arnold Network Autoencoders versus MLP Autoencoders for the analysis of biomedical data\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"university of catanzaro","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-7223313/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7223313/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCurrent research extensively utilises deep learning architectures like Multi-Layer Perceptrons and Convolutional Neural Networks. Topologi- cally, these can be viewed as graphs where node functions are learned, and fixed edges facilitate information flow. A novel architecture, Kolmogorov- Arnold Networks, has been proposed, demonstrating improved performance across various applications by incorporating learnable activation functions on network edges. Ongoing research aims to enhance KANs through fea- tures such as dropout regularisation, Autoencoders, model benchmarking, and the development of KAN Convolutional Networks for matrix convo- lution. This study compares the performance of standard Autoencoders with their Kolmogorov-Arnold counterparts, which possess an equivalent or smaller parameter count, using cardiologic performance signals as input. Specifically, some classic AE tasks such as reconstruction, , denoising, and inpainting, were evaluated on the AbnormalHeartbeat dataset, which comprises audio signals recorded via stethoscope.\u003c/p\u003e","manuscriptTitle":"Comparing Kolmogorov-Arnold Network Autoencoders versus MLP Autoencoders for the analysis of biomedical data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-29 10:21:59","doi":"10.21203/rs.3.rs-7223313/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":"2594211c-9410-4672-91fc-7316d4906973","owner":[],"postedDate":"July 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52294750,"name":"Bioinformatics"},{"id":52294751,"name":"Medical Informatics"}],"tags":[],"updatedAt":"2025-07-29T10:21:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-29 10:21:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7223313","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7223313","identity":"rs-7223313","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}