Fulltext available Open Access
DC FieldValueLanguage
dc.contributor.advisorNeitzke, Michael-
dc.contributor.authorKessener, Daniel
dc.date.accessioned2020-09-29T15:41:06Z-
dc.date.available2020-09-29T15:41:06Z-
dc.date.created2019
dc.date.issued2020-01-13
dc.identifier.urihttp://hdl.handle.net/20.500.12738/9274-
dc.description.abstractIn dieser Arbeit wird die Eignung verschiedener Genetischer Algorithmen der NEAT-Familie für die Optimierung rekurrenter neuronaler Netze untersucht. Dabei werden konkret klassisches NEAT und ES-HyperNEAT in Augenschein genommen. Beide GAs werden mit verschiedenen RNN-Architekturen kombiniert. Konkret werden Long Short-Term Memory und Gated Recurrent Units with Memory Block verwendet. Es werden drei Untersuchungen mit verschiedenen Komplexitätsgraden und Ansprüche an das Erinnerungsvermögen der Agenten durchgeführt, die zeigen, dass GAs sich grundsätzlich gut zum Optimieren von RNNs eignen.de
dc.description.abstractThis paper tests how suited different Genetic Algorithms from the NEAT-family of GAs are to optimize recurrent artificial neural networks. Specifically this paper looks at classic NEAT and ES-HyperNEAT. Both GAs are combined with different RNN architectures - specifically Long Short-Term Memory and Gated Recurrent Units with Memory Block - and subjected to three tests of varying complexities and demands on the memory of the agents. It can be shown that GAs are able to optimize RNN reasonably well.en
dc.language.isodede
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/-
dc.subject.ddc004 Informatik
dc.titleOptimierung rekurrenter neuronaler Netze durch genetische Algorithmen derNEAT-Familiede
dc.typeThesis
openaire.rightsinfo:eu-repo/semantics/openAccess
thesis.grantor.departmentDepartment Informatik
thesis.grantor.placeHamburg
thesis.grantor.universityOrInstitutionHochschule für angewandte Wissenschaften Hamburg
tuhh.contributor.refereePareigis, Stephan-
tuhh.gvk.ppn1687213984
tuhh.identifier.urnurn:nbn:de:gbv:18302-reposit-92762-
tuhh.note.externpubl-mit-pod
tuhh.note.intern1
tuhh.oai.showtrueen_US
tuhh.opus.id5351
tuhh.publication.instituteDepartment Informatik
tuhh.type.opusBachelor Thesis-
dc.subject.gndAlgorithmus
dc.type.casraiSupervised Student Publication-
dc.type.dinibachelorThesis-
dc.type.driverbachelorThesis-
dc.type.statusinfo:eu-repo/semantics/publishedVersion
dc.type.thesisbachelorThesis
dcterms.DCMITypeText-
tuhh.dnb.statusdomain-
item.creatorGNDKessener, Daniel-
item.fulltextWith Fulltext-
item.creatorOrcidKessener, Daniel-
item.grantfulltextopen-
item.cerifentitytypePublications-
item.advisorGNDNeitzke, Michael-
item.languageiso639-1de-
item.openairecristypehttp://purl.org/coar/resource_type/c_46ec-
item.openairetypeThesis-
Appears in Collections:Theses
Files in This Item:
File Description SizeFormat
thesis.pdf1.53 MBAdobe PDFView/Open
Show simple item record

Page view(s)

407
checked on Dec 27, 2024

Download(s)

501
checked on Dec 27, 2024

Google ScholarTM

Check

HAW Katalog

Check

Note about this record


Items in REPOSIT are protected by copyright, with all rights reserved, unless otherwise indicated.