AMG: a memory generation model based on Hebbian plasticity and inferential association

AMG: a memory generation model based on Hebbian plasticity and inferential association | 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 AMG: a memory generation model based on Hebbian plasticity and inferential association Yuankun Liu, Liang Wang, Hangxu Shi, Shaokang Zhang, Haibo Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7843428/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 7 You are reading this latest preprint version Abstract The ability to extract ambiguous memories from past experiences is crucial for cognitive activities in the human brain. This capability is equally important for artificial intelligence agents (AI Agents). Implementing generative models to facilitate the extraction of ambiguous memories can not only enhance the cognitive abilities of AI Agents but also has a positive significance in real life, such as assisting Alzheimer's patients in recovering lost memories from limited cues. This paper proposes a memory association model, named generative associative memory (AMG), which combines Hebbian plasticity and Conditional Deep Convolutional Generative Adversarial Network (CDCGAN). The striking feature of AMG is the ability of simulating the process of memory completion in the human brain. The distinctive idea of AMG is twofold. One is associative memory. The feature vectors of the memories are extracted and stored as key-value pairs within an association matrix constructed based on Hebbian plasticity. The other is inference generation. The association vectors are inferred from the association matrix and used as conditional inputs for CDCGAN, enabling the model to effectively reconstruct the missing components, thereby simulating the memory recovery process observed in the human brain. Experimental results demonstrate that AMG effectively recovers residual memory, achieving a structural similarity index of 0.9951, outperforming non-Hebbian models and reducing total runtime by 9.06%. Memory recovery Hebbian plasticity Long-term memory storage Inferential association Generative model Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 18 Apr, 2026 Reviews received at journal 07 Apr, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers invited by journal 20 Mar, 2026 Editor assigned by journal 20 Mar, 2026 Submission checks completed at journal 13 Oct, 2025 First submitted to journal 12 Oct, 2025 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-7843428","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":610913930,"identity":"65b4192c-1f4c-4dd5-b965-1f8c487e12af","order_by":0,"name":"Yuankun Liu","email":"","orcid":"","institution":"Hebei University","correspondingAuthor":false,"prefix":"","firstName":"Yuankun","middleName":"","lastName":"Liu","suffix":""},{"id":610913931,"identity":"3158752f-c47c-4d96-a53c-2becccc7f9f4","order_by":1,"name":"Liang Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYLCCBxUHEkC0BPFaEs6QrCWxjRQtBsfPHn6ROO9OnsEB5oO3eRjs8ghrOZOXZpG47VmxwQG2ZGsehuRiglrMDuSYGSRuO5y44QCPmTQPw4HEBoJazr8BapkD0sL/jUgtN3KMHyQ2gG1hI06L/Y03ZgwJxw4XSx5mM7acY5BMWItkf47xhw81h/P4jjc/vPGmwo6wFiBgg0QHM4gwIEI9SO0H4tSNglEwCkbBiAUA62tCruTZNoEAAAAASUVORK5CYII=","orcid":"","institution":"Hebei University","correspondingAuthor":true,"prefix":"","firstName":"Liang","middleName":"","lastName":"Wang","suffix":""},{"id":610913932,"identity":"3ca0c1d8-6781-42ad-8e41-3fd2c7c125ad","order_by":2,"name":"Hangxu Shi","email":"","orcid":"","institution":"Hebei University","correspondingAuthor":false,"prefix":"","firstName":"Hangxu","middleName":"","lastName":"Shi","suffix":""},{"id":610913933,"identity":"2afec52b-1c09-4159-a147-03c4a363be9d","order_by":3,"name":"Shaokang Zhang","email":"","orcid":"","institution":"Hebei University","correspondingAuthor":false,"prefix":"","firstName":"Shaokang","middleName":"","lastName":"Zhang","suffix":""},{"id":610913934,"identity":"fdee761c-5586-46af-82d2-cdc4760adaf0","order_by":4,"name":"Haibo Liu","email":"","orcid":"","institution":"Hebei University","correspondingAuthor":false,"prefix":"","firstName":"Haibo","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-10-13 01:23:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7843428/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7843428/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105565290,"identity":"3b6e903c-61cc-4ea3-96bf-bb80a4aeffe4","added_by":"auto","created_at":"2026-03-27 12:52:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":729053,"visible":true,"origin":"","legend":"","description":"","filename":"Menuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7843428/v1_covered_f0794c6b-6fbf-4965-969b-d0d353845997.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AMG: a memory generation model based on\nHebbian plasticity and inferential association","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Memory recovery, Hebbian plasticity, Long-term memory storage, Inferential association, Generative model","lastPublishedDoi":"10.21203/rs.3.rs-7843428/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7843428/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The ability to extract ambiguous memories from past experiences is crucial for cognitive activities in the human brain. This capability is equally important for artificial intelligence agents (AI Agents). Implementing generative models to facilitate the extraction of ambiguous memories can not only enhance the cognitive abilities of AI Agents but also has a positive significance in real life, such as assisting Alzheimer's patients in recovering lost memories from limited cues. This paper proposes a memory association model, named generative associative memory (AMG), which combines Hebbian plasticity and Conditional Deep Convolutional Generative Adversarial Network (CDCGAN). The striking feature of AMG is the ability of simulating the process of memory completion in the human brain. The distinctive idea of AMG is twofold. One is associative memory. The feature vectors of the memories are extracted and stored as key-value pairs within an association matrix constructed based on Hebbian plasticity. The other is inference generation. The association vectors are inferred from the association matrix and used as conditional inputs for CDCGAN, enabling the model to effectively reconstruct the missing components, thereby simulating the memory recovery process observed in the human brain. Experimental results demonstrate that AMG effectively recovers residual memory, achieving a structural similarity index of 0.9951, outperforming non-Hebbian models and reducing total runtime by 9.06\\%.","manuscriptTitle":"AMG: a memory generation model based on\nHebbian plasticity and inferential association","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-25 06:33:55","doi":"10.21203/rs.3.rs-7843428/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-18T20:36:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-07T14:21:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"212945011084496017006686359617415877543","date":"2026-03-20T18:06:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-20T17:24:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-20T17:00:14+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-13T10:15:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2025-10-13T01:11:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"483cd019-3f56-4e85-a161-0e2e1b2ba97c","owner":[],"postedDate":"March 25th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-18T20:38:49+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-25 06:33:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7843428","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7843428","identity":"rs-7843428","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}