Multichannel Matrix Randomized Autoencoder

Multichannel Matrix Randomized Autoencoder | 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Article Multichannel Matrix Randomized Autoencoder Shichen Zhang, Tianlei Wang, Jiuwen Cao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2078071/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 28 Dec, 2022 Read the published version in Neural Processing Letters → Version 1 posted 7 You are reading this latest preprint version Abstract The existing randomized autoencoders (RAEs) are generally designed for vectorization data resulting in destroying the original structure information inevitably when dealing with multi-dimension data such as image and video. To address this issue, a one-side matrix randomized AE (OMRAE) is developed that takes the two-dimensional (2D) data as inputs directly by the linear mapping on one-side of inputs with matrix multiplication. For multichannel 2D (M2D) data, a multichannel OMRAE (OMMRAE) is proposed by training the output weights to rebuild each channel of inputs respectively. In this way, the structural information of each channel and the interaction between channels are explored. Then, a double-side structure using 2 OMMRAEs to simultaneously extracts the row and column structure information of M2D is developed. At last, a novel hierarchical matrix randomized neural networks is constructed for one-class classification (HMRNN-OC) where each layer passes information by bilinear mapping derived from DMMRAE. Experiments are conducted on 2 benchmark datasets for the effectiveness demonstration. Comparisons to several state-of-the-art AEs reveal that the proposed OMMRAE/DMMRAE can obtain better performance with a compact network size. Randomized Autoencoder Matrix Representation Matrix Neural Network One-class classification. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 28 Dec, 2022 Read the published version in Neural Processing Letters → Version 1 posted Editorial decision: Major revision 15 Nov, 2022 Reviews received at journal 09 Nov, 2022 Reviewers agreed at journal 25 Oct, 2022 Reviewers invited by journal 25 Oct, 2022 Editor assigned by journal 18 Sep, 2022 Submission checks completed at journal 18 Sep, 2022 First submitted to journal 18 Sep, 2022 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-2078071","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":137648050,"identity":"0d17b79e-a4f3-4819-979b-14b016cdd867","order_by":0,"name":"Shichen Zhang","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shichen","middleName":"","lastName":"Zhang","suffix":""},{"id":137648051,"identity":"b41a2f3f-07ec-4f1d-870f-e262d68537b5","order_by":1,"name":"Tianlei Wang","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tianlei","middleName":"","lastName":"Wang","suffix":""},{"id":137648052,"identity":"75a32960-211c-4e46-8a1f-6154a17efe0e","order_by":2,"name":"Jiuwen Cao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYBACxgYQWXEATEuQoOUMKVog+tpI0cI8I/nhh4/z7shuOMB88DYPg10eYQtmpBlLztz2zHjDAbZkax6G5GLCWmbnMEjzbjucuOEAj5k0D8OBxAYitDD/5p0D0sL/jWgtbNK8DWBb2IjUMv+ZmeWMY4eNZx5mM7acY5BMWIthz+HHNz7UHJbtO9788MabCjsitMBVMIMIA0LqgUCeCDWjYBSMglEw0gEAijRAHaXSbioAAAAASUVORK5CYII=","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Jiuwen","middleName":"","lastName":"Cao","suffix":""}],"badges":[],"createdAt":"2022-09-18 14:59:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2078071/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2078071/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11063-022-11134-8","type":"published","date":"2022-12-28T18:07:17+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":26880298,"identity":"840cef17-4aec-4013-805f-82dc25c7a47a","added_by":"auto","created_at":"2022-09-23 14:24:48","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2720331,"visible":true,"origin":"","legend":"","description":"","filename":"MatrixRandomizedAutoencoderforNPL.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2078071/v1_covered.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multichannel Matrix Randomized Autoencoder","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-2078071/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"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":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Randomized Autoencoder, Matrix Representation, Matrix Neural Network, One-class classification.","lastPublishedDoi":"10.21203/rs.3.rs-2078071/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2078071/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The existing randomized autoencoders (RAEs) are generally designed for vectorization data resulting in destroying the original structure information inevitably when dealing with multi-dimension data such as image and video. To address this issue, a one-side matrix randomized AE (OMRAE) is developed that takes the two-dimensional (2D) data as inputs directly by the linear mapping on one-side of inputs with matrix multiplication. For multichannel 2D (M2D) data, a multichannel OMRAE (OMMRAE) is proposed by training the output weights to rebuild each channel of inputs respectively. In this way, the structural information of each channel and the interaction between channels are explored. Then, a double-side structure using 2 OMMRAEs to simultaneously extracts the row and column structure information of M2D is developed. At last, a novel hierarchical matrix randomized neural networks is constructed for one-class classification (HMRNN-OC) where each layer passes information by bilinear mapping derived from DMMRAE. Experiments are conducted on 2 benchmark datasets for the effectiveness demonstration. Comparisons to several state-of-the-art AEs reveal that the proposed OMMRAE/DMMRAE can obtain better performance with a compact network size.","manuscriptTitle":"Multichannel Matrix Randomized Autoencoder","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-09-23 14:24:41","doi":"10.21203/rs.3.rs-2078071/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2022-11-15T07:45:16+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2022-11-10T02:59:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62052dda-dec2-43a4-adf9-cdc6abf23987","date":"2022-10-26T03:23:43+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2022-10-26T03:08:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2022-09-19T01:30:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-09-19T01:30:19+00:00","index":"","fulltext":""},{"type":"submitted","content":"Neural Processing Letters","date":"2022-09-18T14:57:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f2381815-1c24-419f-ad04-a8e4295bdb54","owner":[],"postedDate":"September 23rd, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-10-16T18:12:18+00:00","versionOfRecord":{"articleIdentity":"rs-2078071","link":"https://doi.org/10.1007/s11063-022-11134-8","journal":{"identity":"neural-processing-letters","isVorOnly":false,"title":"Neural Processing Letters"},"publishedOn":"2022-12-28 18:07:17","publishedOnDateReadable":"December 28th, 2022"},"versionCreatedAt":"2022-09-23 14:24:41","video":"","vorDoi":"10.1007/s11063-022-11134-8","vorDoiUrl":"https://doi.org/10.1007/s11063-022-11134-8","workflowStages":[]},"version":"v1","identity":"rs-2078071","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2078071","identity":"rs-2078071","version":["v1"]},"buildId":"WrCJVZZCHTDjtuVLN7oU0","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}