000890994 001__ 890994
000890994 005__ 20240313103111.0
000890994 0247_ $$2doi$$a10.3389/fncom.2021.543872
000890994 0247_ $$2Handle$$a2128/28017
000890994 0247_ $$2altmetric$$aaltmetric:102089502
000890994 0247_ $$2pmid$$a33746728
000890994 0247_ $$2WOS$$aWOS:000629977000001
000890994 037__ $$aFZJ-2021-01301
000890994 082__ $$a610
000890994 1001_ $$0P:(DE-Juel1)162278$$aWeidel, Philipp$$b0
000890994 245__ $$aUnsupervised Learning and Clustered Connectivity Enhance Reinforcement Learning in Spiking Neural Networks
000890994 260__ $$aLausanne$$bFrontiers Research Foundation$$c2021
000890994 3367_ $$2DRIVER$$aarticle
000890994 3367_ $$2DataCite$$aOutput Types/Journal article
000890994 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1642001841_14168
000890994 3367_ $$2BibTeX$$aARTICLE
000890994 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000890994 3367_ $$00$$2EndNote$$aJournal Article
000890994 520__ $$aReinforcement learning is a paradigm that can account for how organisms learn to adapt their behavior in complex environments with sparse rewards. To partition an environment into discrete states, implementations in spiking neuronal networks typically rely on input architectures involving place cells or receptive fields specified ad hoc by the researcher. This is problematic as a model for how an organism can learn appropriate behavioral sequences in unknown environments, as it fails to account for the unsupervised and self-organized nature of the required representations. Additionally, this approach presupposes knowledge on the part of the researcher on how the environment should be partitioned and represented and scales poorly with the size or complexity of the environment. To address these issues and gain insights into how the brain generates its own task-relevant mappings, we propose a learning architecture that combines unsupervised learning on the input projections with biologically motivated clustered connectivity within the representation layer. This combination allows input features to be mapped to clusters; thus the network self-organizes to produce clearly distinguishable activity patterns that can serve as the basis for reinforcement learning on the output projections. On the basis of the MNIST and Mountain Car tasks, we show that our proposed model performs better than either a comparable unclustered network or a clustered network with static input projections. We conclude that the combination of unsupervised learning and clustered connectivity provides a generic representational substrate suitable for further computation.
000890994 536__ $$0G:(DE-HGF)POF4-523$$a523 - Neuromorphic Computing and Network Dynamics (POF4-523)$$cPOF4-523$$fPOF IV$$x0
000890994 536__ $$0G:(DE-HGF)POF2-89574$$a89574 - Theory, modelling and simulation (POF2-89574)$$cPOF2-89574$$fPOF II T$$x1
000890994 536__ $$0G:(DE-Juel1)jinm60_20190501$$aFunctional Neural Architectures (jinm60_20190501)$$cjinm60_20190501$$fFunctional Neural Architectures$$x2
000890994 536__ $$0G:(DE-HGF)POF4-5232$$a5232 - Computational Principles (POF4-523)$$cPOF4-523$$fPOF IV$$x3
000890994 588__ $$aDataset connected to CrossRef
000890994 7001_ $$0P:(DE-Juel1)165640$$aDuarte, Renato$$b1$$eCorresponding author$$ufzj
000890994 7001_ $$0P:(DE-Juel1)151166$$aMorrison, Abigail$$b2$$ufzj
000890994 773__ $$0PERI:(DE-600)2452964-3$$a10.3389/fncom.2021.543872$$gVol. 15, p. 543872$$p543872$$tFrontiers in computational neuroscience$$v15$$x1662-5188$$y2021
000890994 8564_ $$uhttps://juser.fz-juelich.de/record/890994/files/fncom-15-543872.pdf$$yOpenAccess
000890994 8767_ $$d2021-03-29$$eAPC$$jDeposit$$lDeposit: Frontiers$$z$ 2507.50
000890994 909CO $$ooai:juser.fz-juelich.de:890994$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000890994 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165640$$aForschungszentrum Jülich$$b1$$kFZJ
000890994 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)151166$$aForschungszentrum Jülich$$b2$$kFZJ
000890994 9130_ $$0G:(DE-HGF)POF2-89574$$1G:(DE-HGF)POF3-890$$2G:(DE-HGF)POF3-800$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vTheory, modelling and simulation$$x0
000890994 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
000890994 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5232$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x1
000890994 9141_ $$y2021
000890994 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2020-09-03
000890994 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000890994 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bFRONT COMPUT NEUROSC : 2018$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000890994 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central$$d2020-09-03
000890994 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2020-09-03
000890994 920__ $$lyes
000890994 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x0
000890994 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lTheoretical Neuroscience$$x1
000890994 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x2
000890994 9201_ $$0I:(DE-82)080012_20140620$$kJARA-HPC$$lJARA - HPC$$x3
000890994 9801_ $$aAPC
000890994 9801_ $$aFullTexts
000890994 980__ $$ajournal
000890994 980__ $$aVDB
000890994 980__ $$aI:(DE-Juel1)INM-6-20090406
000890994 980__ $$aI:(DE-Juel1)IAS-6-20130828
000890994 980__ $$aI:(DE-Juel1)INM-10-20170113
000890994 980__ $$aI:(DE-82)080012_20140620
000890994 980__ $$aAPC
000890994 980__ $$aUNRESTRICTED
000890994 981__ $$aI:(DE-Juel1)IAS-6-20130828