L-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding

L-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding | 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 L-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding Alexander Stuy, Nodin Weddington This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9519230/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 An artificial world of barriers and plains scattered with food is used to test the feasibility of using genetic algorithms to optimize hebbian neural networks to perform on problems without apriori knowledge of the problem domain. A formal L-System based genetic alphabet for neural networks, titled Lsys, and a neural network genetic modeling tool titled Wp1hgn are introduced. Lsys and Matrix neural network topology genetic encoding methods are compared across 24 experimental runs. Lsys encoding achieved a mean maximum food count of 3802 ± 197 at generation 1000 across 8 runs with varied parameters, compared to 1388 ± 610 for Matrix encoding, a 2.74x performance advantage with an 8.5-fold improvement in consistency as measured by coefficient of variation (5.2% vs 44.0%). All 8 Lsys populations successfully learned to navigate the environment, while 4 of 8 Matrix populations failed to achieve competitive performance at any point during 1000 generations. When transferred to a novel maze environment, Lsys populations demonstrated immediate robust generalization, achieving a mean maximum food count of 2455 ± 176 compared to 422 ± 212 for Matrix populations, a 5.82x advantage that exceeded the training world performance gap. A MatrixLSG control condition, in which initial populations were generated using Lsys genotypes and then evolved using Matrix operators, demonstrated that the performance advantage of Lsys encoding derives primarily from the genetic algorithm operating on the compressed symbolic Lsys alphabet throughout evolution rather than from initial population structure. Lsys encoding is shown to provide faster convergence, higher peak performance, dramatically greater reliability, and superior generalization to novel environments compared to Matrix encoding across all experimental conditions tested. Artificial Intelligence and Machine Learning Neural Network Genetic Optimization L-Systems 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-9519230","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":629131346,"identity":"10dd3da2-4388-4ec7-84d2-1f0c8ffa289d","order_by":0,"name":"Alexander Stuy","email":"","orcid":"https://orcid.org/0009-0003-4801-2377","institution":"Florida State University","correspondingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Stuy","suffix":""},{"id":629131347,"identity":"2340fe79-714e-4071-93a9-7374b4fae0ec","order_by":1,"name":"Nodin Weddington","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAUlEQVRIiWNgGAWjYJACCR4DMM34gLEBSDEfAHGYCWvhAaoyAGthSyBGCwNYC5sEUVrMJZIP3nhTcMduP3vvsYqfO2yiGdjYn0kwVFgnNuDQYjkjLdlyjsGz5B6ec2k3e8+k5Taw8ZhJMJxJx6nF4HaOmTSPweFkHokcs9uMbYdzG+R7gC5sO4xHS/43uJZixrb/QFuADmP8h09LDhtIix1ICzNj2wGgFgYzYDjg0XL/mTHQL4cTeM6cMZbsbUvObWPjMbZIOJZujFPLmcMPb7z5c9ievb3H8MPPNrvcfjb2hzc+1FjL4tICAwhnsIGIBALKQcCeCDWjYBSMglEwUgEAjohW7PljNrkAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0002-0884-5764","institution":"Florida State University","correspondingAuthor":true,"prefix":"","firstName":"Nodin","middleName":"","lastName":"Weddington","suffix":""}],"badges":[],"createdAt":"2026-04-24 16:11:24","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-9519230/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9519230/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107849089,"identity":"586c5656-c3f5-466f-a7b8-97f9219a00c0","added_by":"auto","created_at":"2026-04-27 01:39:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":678749,"visible":true,"origin":"","legend":"","description":"","filename":"LSystemGeneticEncodingforScalableNeuralNetworkEvolutionAComparisonwithDirectMatrixEncoding.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9519230/v1_covered_f34bbefd-9ff2-401a-a547-eea0323a0cb2.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eL-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Neural Network, Genetic Optimization, L-Systems","lastPublishedDoi":"10.21203/rs.3.rs-9519230/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9519230/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAn artificial world of barriers and plains scattered with food is used to test the feasibility of using genetic algorithms to optimize hebbian neural networks to perform on problems without apriori knowledge of the problem domain. A formal L-System based genetic alphabet for neural networks, titled Lsys, and a neural network genetic modeling tool titled Wp1hgn are introduced. Lsys and Matrix neural network topology genetic encoding methods are compared across 24 experimental runs. Lsys encoding achieved a mean maximum food count of 3802 ± 197 at generation 1000 across 8 runs with varied parameters, compared to 1388 ± 610 for Matrix encoding, a 2.74x performance advantage with an 8.5-fold improvement in consistency as measured by coefficient of variation (5.2% vs 44.0%). All 8 Lsys populations successfully learned to navigate the environment, while 4 of 8 Matrix populations failed to achieve competitive performance at any point during 1000 generations. When transferred to a novel maze environment, Lsys populations demonstrated immediate robust generalization, achieving a mean maximum food count of 2455 ± 176 compared to 422 ± 212 for Matrix populations, a 5.82x advantage that exceeded the training world performance gap. A MatrixLSG control condition, in which initial populations were generated using Lsys genotypes and then evolved using Matrix operators, demonstrated that the performance advantage of Lsys encoding derives primarily from the genetic algorithm operating on the compressed symbolic Lsys alphabet throughout evolution rather than from initial population structure. Lsys encoding is shown to provide faster convergence, higher peak performance, dramatically greater reliability, and superior generalization to novel environments compared to Matrix encoding across all experimental conditions tested.\u003c/p\u003e","manuscriptTitle":"L-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 01:38:19","doi":"10.21203/rs.3.rs-9519230/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":"0828fe7e-2143-45e7-942d-08479ce0c122","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66968105,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-04-27T01:38:19+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 01:38:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9519230","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9519230","identity":"rs-9519230","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}