Dragonfly Visual Attention-Merged Evolutionary Neural Network: Biomimetic Optimizer Solving LSGO problems

Dragonfly Visual Attention-Merged Evolutionary Neural Network: Biomimetic Optimizer Solving LSGO problems | 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 Dragonfly Visual Attention-Merged Evolutionary Neural Network: Biomimetic Optimizer Solving LSGO problems Zhuhong Zhang, Heng Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4998609/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 biological visual system includes a variety of motion-sensitive neurons that intrinsically perceive changes in visual motion. Although some of their neurophysiological findings have been successfully used to construct computational models for engineering applications targeting specific problems, it remains unclear how the relevant response mechanisms can be used to optimize the subject. Hereby, related to grayscale intensity difference, the dragonfly visual information-processing and attention mechanisms are borrowed to develop a feedforward dragonfly visual attention-merged neural network with presynaptic and postsynaptic neural subnetworks, which can characterize changes of visual motion in terms of the on-line output activities named learning rates. Afterwards, integrated such learning rates into a new-type and metaheuristics-inspired state transition strategy, a dragonfly attention-merged visual evolutionary neural network with the unique parameter of input resolution, which enables current states to discover the global optimum quickly, is developed to solve large-scale global optimization (LSGO) and even hyperdimensional global optimization (HDGO) problems. The theoretical analysis implicates that the evolutionary neural network’s complexity is mainly decided by the optimization problem itself. Comparative experiments have validated that it, as a highly competitive optimizer, can significantly outperform the compared approaches and successfully solve the design optimization problem of a complex sixth-order analog active filter. Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Computational neuroscience Dragonfly visual system Mechanisms of visual attention-merged Visual evolutionary neural network HDGO Analog active filter. 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-4998609","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":360619472,"identity":"2ee3dec5-7c94-467f-9c72-d7c3f6733656","order_by":0,"name":"Zhuhong Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYDACCQY2ECUH4bGRoMWYdC2JDURrkZ/d/uzBzx216fP9zxgwfCg7zMA/uwG/FsY5B9INe88cz9144IwB44xzhxkk7hzAr4VZIuGYBG/bsdyNjT0GzLxthxkMJBLwa2GTSGyT/Nt2LN2wmceA+S8xWngkktmkedtqEuTZgFoYidEiIZHGJi3bdsBwAw9bwcGec+k8EjcIaJGfkf5M8m1bnbx8/+GND36UWcvxzyCgBQqA7jnAwHAA5FKi1ANBHYN8A7FqR8EoGAWjYMQBAGBAP2O16udOAAAAAElFTkSuQmCC","orcid":"","institution":"Guizhou University","correspondingAuthor":true,"prefix":"","firstName":"Zhuhong","middleName":"","lastName":"Zhang","suffix":""},{"id":360619473,"identity":"46a060a6-4dd0-4d71-8077-4b8da86c1c5b","order_by":1,"name":"Heng Wang","email":"","orcid":"","institution":"Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"Heng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-08-29 14:57:00","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4998609/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4998609/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72130908,"identity":"12b8f272-2c94-496e-85d1-9e9f9f16a00b","added_by":"auto","created_at":"2024-12-23 04:09:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1460307,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript829.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4998609/v1_covered_6299f636-7d68-4067-9ad6-e20198966ab3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dragonfly Visual Attention-Merged Evolutionary Neural Network: Biomimetic Optimizer Solving LSGO problems","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":"Dragonfly visual system, Mechanisms of visual attention-merged, Visual evolutionary neural network, HDGO, Analog active filter. ","lastPublishedDoi":"10.21203/rs.3.rs-4998609/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4998609/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The biological visual system includes a variety of motion-sensitive neurons that intrinsically perceive changes in visual motion. Although some of their neurophysiological findings have been successfully used to construct computational models for engineering applications targeting specific problems, it remains unclear how the relevant response mechanisms can be used to optimize the subject. Hereby, related to grayscale intensity difference, the dragonfly visual information-processing and attention mechanisms are borrowed to develop a feedforward dragonfly visual attention-merged neural network with presynaptic and postsynaptic neural subnetworks, which can characterize changes of visual motion in terms of the on-line output activities named learning rates. Afterwards, integrated such learning rates into a new-type and metaheuristics-inspired state transition strategy, a dragonfly attention-merged visual evolutionary neural network with the unique parameter of input resolution, which enables current states to discover the global optimum quickly, is developed to solve large-scale global optimization (LSGO) and even hyperdimensional global optimization (HDGO) problems. The theoretical analysis implicates that the evolutionary neural network’s complexity is mainly decided by the optimization problem itself. Comparative experiments have validated that it, as a highly competitive optimizer, can significantly outperform the compared approaches and successfully solve the design optimization problem of a complex sixth-order analog active filter.","manuscriptTitle":"Dragonfly Visual Attention-Merged Evolutionary Neural Network: Biomimetic Optimizer Solving LSGO problems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-10 10:48:06","doi":"10.21203/rs.3.rs-4998609/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":"a34e4b89-7568-4045-b4dc-8e49bc628036","owner":[],"postedDate":"October 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":38363125,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":38363126,"name":"Biological sciences/Computational biology and bioinformatics/Computational neuroscience"}],"tags":[],"updatedAt":"2024-12-23T04:08:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-10 10:48:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4998609","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4998609","identity":"rs-4998609","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}