000910130 001__ 910130
000910130 005__ 20240705080646.0
000910130 0247_ $$2doi$$a10.3389/fncom.2022.885207
000910130 0247_ $$2Handle$$a2128/32022
000910130 0247_ $$2pmid$$a35720775
000910130 0247_ $$2WOS$$aWOS:000811824200001
000910130 037__ $$aFZJ-2022-03626
000910130 041__ $$aEnglish
000910130 082__ $$a610
000910130 1001_ $$0P:(DE-Juel1)161462$$aYegenoglu, Alper$$b0$$eCorresponding author
000910130 245__ $$aExploring Parameter and Hyper-Parameter Spaces of Neuroscience Models on High Performance Computers With Learning to Learn
000910130 260__ $$aLausanne$$bFrontiers Research Foundation$$c2022
000910130 3367_ $$2DRIVER$$aarticle
000910130 3367_ $$2DataCite$$aOutput Types/Journal article
000910130 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1719988004_14554
000910130 3367_ $$2BibTeX$$aARTICLE
000910130 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000910130 3367_ $$00$$2EndNote$$aJournal Article
000910130 520__ $$aNeuroscience models commonly have a high number of degrees of freedom and only specific regions within the parameter space are able to produce dynamics of interest. This makes the development of tools and strategies to efficiently find these regions of high importance to advance brain research. Exploring the high dimensional parameter space using numerical simulations has been a frequently used technique in the last years in many areas of computational neuroscience. Today, high performance computing (HPC) can provide a powerful infrastructure to speed up explorations and increase our general understanding of the behavior of the model in reasonable times. Learning to learn (L2L) is a well-known concept in machine learning (ML) and a specific method for acquiring constraints to improve learning performance. This concept can be decomposed into a two loop optimization process where the target of optimization can consist of any program such as an artificial neural network, a spiking network, a single cell model, or a whole brain simulation. In this work, we present L2L as an easy to use and flexible framework to perform parameter and hyper-parameter space exploration of neuroscience models on HPC infrastructure. Learning to learn is an implementation of the L2L concept written in Python. This open-source software allows several instances of an optimization target to be executed with different parameters in an embarrassingly parallel fashion on HPC. L2L provides a set of built-in optimizer algorithms, which make adaptive and efficient exploration of parameter spaces possible. Different from other optimization toolboxes, L2L provides maximum flexibility for the way the optimization target can be executed. In this paper, we show a variety of examples of neuroscience models being optimized within the L2L framework to execute different types of tasks. The tasks used to illustrate the concept go from reproducing empirical data to learning how to solve a problem in a dynamic environment. We particularly focus on simulations with models ranging from the single cell to the whole brain and using a variety of simulation engines like NEST, Arbor, TVB, OpenAIGym, and NetLogo.
000910130 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000910130 536__ $$0G:(EU-Grant)785907$$aHBP SGA2 - Human Brain Project Specific Grant Agreement 2 (785907)$$c785907$$fH2020-SGA-FETFLAG-HBP-2017$$x1
000910130 536__ $$0G:(EU-Grant)945539$$aHBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539)$$c945539$$fH2020-SGA-FETFLAG-HBP-2019$$x2
000910130 536__ $$0G:(DE-Juel1)JL SMHB-2021-2027$$aJL SMHB - Joint Lab Supercomputing and Modeling for the Human Brain (JL SMHB-2021-2027)$$cJL SMHB-2021-2027$$x3
000910130 536__ $$0G:(DE-Juel1)Helmholtz-SLNS$$aSLNS - SimLab Neuroscience (Helmholtz-SLNS)$$cHelmholtz-SLNS$$x4
000910130 536__ $$0G:(EU-Grant)800858$$aICEI - Interactive Computing E-Infrastructure for the Human Brain Project (800858)$$c800858$$fH2020-SGA-INFRA-FETFLAG-HBP$$x5
000910130 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x6
000910130 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000910130 7001_ $$0P:(DE-HGF)0$$aSubramoney, Anand$$b1
000910130 7001_ $$0P:(DE-Juel1)176815$$aHater, Thorsten$$b2$$ufzj
000910130 7001_ $$0P:(DE-Juel1)184894$$aJimenez-Romero, Cristian$$b3$$ufzj
000910130 7001_ $$0P:(DE-Juel1)168169$$aKlijn, Wouter$$b4$$ufzj
000910130 7001_ $$0P:(DE-Juel1)184896$$aPérez Martín, Aarón$$b5$$ufzj
000910130 7001_ $$0P:(DE-Juel1)179447$$avan der Vlag, Michiel$$b6$$ufzj
000910130 7001_ $$0P:(DE-HGF)0$$aHerty, Michael$$b7
000910130 7001_ $$0P:(DE-Juel1)151166$$aMorrison, Abigail$$b8$$ufzj
000910130 7001_ $$0P:(DE-Juel1)165859$$aDiaz, Sandra$$b9$$ufzj
000910130 773__ $$0PERI:(DE-600)2452964-3$$a10.3389/fncom.2022.885207$$gVol. 16, p. 885207$$p885207$$tFrontiers in computational neuroscience$$v16$$x1662-5188$$y2022
000910130 8564_ $$uhttps://juser.fz-juelich.de/record/910130/files/fncom-16-885207.pdf$$yOpenAccess
000910130 8767_ $$d2022-12-27$$eAPC$$jDeposit$$z2507,50 USD
000910130 909CO $$ooai:juser.fz-juelich.de:910130$$pdnbdelivery$$popenCost$$pec_fundedresources$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)161462$$aForschungszentrum Jülich$$b0$$kFZJ
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176815$$aForschungszentrum Jülich$$b2$$kFZJ
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184894$$aForschungszentrum Jülich$$b3$$kFZJ
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)168169$$aForschungszentrum Jülich$$b4$$kFZJ
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184896$$aForschungszentrum Jülich$$b5$$kFZJ
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)179447$$aForschungszentrum Jülich$$b6$$kFZJ
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)151166$$aForschungszentrum Jülich$$b8$$kFZJ
000910130 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165859$$aForschungszentrum Jülich$$b9$$kFZJ
000910130 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
000910130 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x1
000910130 9141_ $$y2022
000910130 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
000910130 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
000910130 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
000910130 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-05-04
000910130 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2021-05-04
000910130 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000910130 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-05-04
000910130 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2021-05-04
000910130 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000910130 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2021-05-04
000910130 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bFRONT COMPUT NEUROSC : 2021$$d2022-11-09
000910130 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-09
000910130 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-09
000910130 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-05-13T10:43:05Z
000910130 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-05-13T10:43:05Z
000910130 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2021-05-13T10:43:05Z
000910130 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-09
000910130 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-09
000910130 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2022-11-09
000910130 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2022-11-09
000910130 920__ $$lno
000910130 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000910130 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lComputational and Systems Neuroscience$$x1
000910130 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x2
000910130 980__ $$ajournal
000910130 980__ $$aVDB
000910130 980__ $$aI:(DE-Juel1)JSC-20090406
000910130 980__ $$aI:(DE-Juel1)IAS-6-20130828
000910130 980__ $$aI:(DE-Juel1)INM-6-20090406
000910130 980__ $$aAPC
000910130 980__ $$aUNRESTRICTED
000910130 9801_ $$aAPC
000910130 9801_ $$aFullTexts
000910130 981__ $$aI:(DE-Juel1)IAS-6-20130828