Total recall: Post-processing methods for delay-embedding and feature scaling of reservoir computer

Total recall: Post-processing methods for delay-embedding and feature scaling of reservoir computer | 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 Total recall: Post-processing methods for delay-embedding and feature scaling of reservoir computer Jonnel Anthony Jaurigue, Joshua Robertson, Antonio Hurtado, Lina Jaurigue, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4741218/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Reservoir computing is a machine learning method that is well-suited for complex timeseries prediction tasks. Both delay-embedding and the projection of input data into a higher-dimensional space play important roles in enabling accurate predictions. We establish simple post-processing methods that train on past node states, chosen at either uniformly or randomly-delayed timeshifts. Reservoir computer prediction performance is improved through increased feature dimension and/or better delay-embedding. From these simple post-processing methods we introduce the multi-random-timeshifting method, which recalls previous states of reservoir nodes. Multi-random-timeshifting allows for smaller reservoirs while maintaining large feature dimensions, is computationally cheap to optimise, and is our preferred post-processing method. All our post-processing methods can be translated to readout data sampled from physical reservoirs, which we demonstrate using readout data from an experimentally-realised laser reservoir system. Physical sciences/Mathematics and computing/Computational science Physical sciences/Physics/Applied physics Physical sciences/Physics/Optical physics Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Under Review 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-4741218","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":334815940,"identity":"24abf5c9-0497-4736-8938-9690d9bacd79","order_by":0,"name":"Jonnel Anthony Jaurigue","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0003-0802-076X","institution":"Technische Universität Ilmenau","correspondingAuthor":true,"prefix":"","firstName":"Jonnel","middleName":"Anthony","lastName":"Jaurigue","suffix":""},{"id":334815941,"identity":"bb674adb-913d-48f5-9adc-00d3f53b685b","order_by":1,"name":"Joshua Robertson","email":"","orcid":"","institution":"Technische Universitä","correspondingAuthor":false,"prefix":"","firstName":"Joshua","middleName":"","lastName":"Robertson","suffix":""},{"id":334815942,"identity":"78817ab4-7594-456f-88c4-d40c04dff6c7","order_by":2,"name":"Antonio Hurtado","email":"","orcid":"https://orcid.org/0000-0002-4448-9034","institution":"University of Strathclyde","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"","lastName":"Hurtado","suffix":""},{"id":334815943,"identity":"91cc5c3c-25ec-471b-868f-aef91d92394e","order_by":3,"name":"Lina Jaurigue","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Lina","middleName":"","lastName":"Jaurigue","suffix":""},{"id":334815944,"identity":"37708447-cd11-4be2-864e-f6f9b89c4bbb","order_by":4,"name":"Kathy Lüdge","email":"","orcid":"https://orcid.org/0000-0002-4831-8910","institution":"Technische Univ. Ilmenau","correspondingAuthor":false,"prefix":"","firstName":"Kathy","middleName":"","lastName":"Lüdge","suffix":""}],"badges":[],"createdAt":"2024-07-15 07:00:57","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4741218/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4741218/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":63431820,"identity":"4003e2b6-ea94-4155-a5ec-dd8bb46164b2","added_by":"auto","created_at":"2024-08-28 05:25:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2255439,"visible":true,"origin":"","legend":"","description":"","filename":"JAU24b3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4741218/v1_covered_c0162113-18d7-4b3e-ad34-7d4268770681.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Total recall: Post-processing methods for delay-embedding and feature scaling of\r\nreservoir computer","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-4741218/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4741218/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Reservoir computing is a machine learning method that is well-suited for complex timeseries prediction tasks. Both delay-embedding and the projection of input data into a higher-dimensional space play important roles in enabling accurate predictions. We establish simple post-processing methods that train on past node states, chosen at either uniformly or randomly-delayed timeshifts. Reservoir computer prediction performance is improved through increased feature dimension and/or better delay-embedding. From these simple post-processing methods we introduce the multi-random-timeshifting method, which recalls previous states of reservoir nodes. Multi-random-timeshifting allows for smaller reservoirs while maintaining large feature dimensions, is computationally cheap to optimise, and is our preferred post-processing method. All our post-processing methods can be translated to readout data sampled from physical reservoirs, which we demonstrate using readout data from an experimentally-realised laser reservoir system.","manuscriptTitle":"Total recall: Post-processing methods for delay-embedding and feature scaling of\nreservoir computer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-28 05:00:52","doi":"10.21203/rs.3.rs-4741218/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"communications-engineering","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"commseng","sideBox":"Learn more about [Communications Engineering](http://link.springer.com/journal/44172)","snPcode":"44172","submissionUrl":"https://mts-commseng.nature.com/cgi-bin/main.plex","title":"Communications Engineering","twitterHandle":"@commseng","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2bd9b910-fe71-4f86-830a-50c9b4c26550","owner":[],"postedDate":"August 28th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":35457823,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":35457824,"name":"Physical sciences/Physics/Applied physics"},{"id":35457825,"name":"Physical sciences/Physics/Optical physics"}],"tags":[],"updatedAt":"2024-12-04T12:37:31+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-28 05:00:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4741218","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4741218","identity":"rs-4741218","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}