001009096 001__ 1009096
001009096 005__ 20230717203559.0
001009096 020__ $$a978-953-233-104-2
001009096 0247_ $$2doi$$a10.23919/MIPRO57284.2023.10159755
001009096 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-02635
001009096 037__ $$aFZJ-2023-02635
001009096 041__ $$aEnglish
001009096 1001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b0$$eCorresponding author
001009096 1112_ $$a46th MIPRO ICT and Electronics Convention$$cOpatija$$d2023-05-22 - 2023-05-26$$gMIPRO 2023$$wCroatia
001009096 245__ $$aEnabling Hyperparameter-Tuning of AI Models for Healthcare using the CoE RAISE Unique AI Framework for HPC
001009096 260__ $$bIEEE$$c2023
001009096 29510 $$a2023 46th MIPRO ICT and Electronics Convention (MIPRO)
001009096 300__ $$a435-440
001009096 3367_ $$2ORCID$$aCONFERENCE_PAPER
001009096 3367_ $$033$$2EndNote$$aConference Paper
001009096 3367_ $$2BibTeX$$aINPROCEEDINGS
001009096 3367_ $$2DRIVER$$aconferenceObject
001009096 3367_ $$2DataCite$$aOutput Types/Conference Paper
001009096 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1689596656_1160
001009096 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
001009096 520__ $$aThe European Center of Excellence in Exascale Computing "Research on AI- and Simulation-Based Engineering at Exascale" (CoE RAISE) is a project funded by the European Commission. One of its central goals is to develop a Unique AI Framework (UAIF) that simplifies the development of AI models on cutting-edge supercomputers. However, those supercomputers’ High-Performance Computing (HPC) environments require the knowledge of many low-level modules that all need to work together in different software versions (e.g., TensorFlow, Python, NCCL, PyTorch) and various concrete supercomputer hardware deployments (e.g., JUWELS, JURECA, DEEP, JUPITER and other EuroHPC Joint Undertaking HPC resources). This paper will describe our analyzed complex challenges for AI researchers using those environments and explain how to overcome them using the UAIF. In addition, it will show the benefits of using the UAIF hypertuning capability to make AI models better (i.e., better parameters) and faster by using HPC. Also, to demonstrate that the UAIF approach is indeed simple, we describe the adoption of selected UAIF building blocks by healthcare applications. The examples include AI models for the Acute Respiratory Distress Syndrome (ARDS). Finally, we highlight other AI models of use cases that co-designed the UAIF.
001009096 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001009096 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x1
001009096 536__ $$0G:(EU-Grant)951733$$aRAISE - Research on AI- and Simulation-Based Engineering at Exascale (951733)$$c951733$$fH2020-INFRAEDI-2019-1$$x2
001009096 536__ $$0G:(BMBF)01ZZ1803B$$aBMBF 01ZZ1803B - SMITH - Medizininformatik-Konsortium - Beitrag Universitätsklinikum Aachen (01ZZ1803B)$$c01ZZ1803B$$x3
001009096 588__ $$aDataset connected to CrossRef Conference
001009096 7001_ $$0P:(DE-Juel1)178934$$aBarakat, C.$$b1
001009096 7001_ $$0P:(DE-Juel1)185651$$aFritsch, S.$$b2
001009096 7001_ $$0P:(DE-Juel1)180916$$aAach, M.$$b3
001009096 7001_ $$0P:(DE-Juel1)185652$$aBusch, J.$$b4
001009096 7001_ $$0P:(DE-Juel1)165948$$aLintermann, A.$$b5
001009096 7001_ $$0P:(DE-HGF)0$$aSchuppert, A.$$b6
001009096 7001_ $$0P:(DE-HGF)0$$aBrynjólfsson, S.$$b7
001009096 7001_ $$0P:(DE-HGF)0$$aNeukirchen, H.$$b8
001009096 7001_ $$0P:(DE-HGF)0$$aBook, M.$$b9
001009096 773__ $$a10.23919/MIPRO57284.2023.10159755
001009096 8564_ $$uhttps://juser.fz-juelich.de/record/1009096/files/MIPRO2023__RAISE_UAIF_Paper.pdf$$yOpenAccess
001009096 909CO $$ooai:juser.fz-juelich.de:1009096$$popenaire$$popen_access$$pdriver$$pVDB$$pec_fundedresources$$pdnbdelivery
001009096 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b0$$kFZJ
001009096 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178934$$aForschungszentrum Jülich$$b1$$kFZJ
001009096 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185651$$aForschungszentrum Jülich$$b2$$kFZJ
001009096 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180916$$aForschungszentrum Jülich$$b3$$kFZJ
001009096 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185652$$aForschungszentrum Jülich$$b4$$kFZJ
001009096 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165948$$aForschungszentrum Jülich$$b5$$kFZJ
001009096 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b6$$kRWTH
001009096 9131_ $$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
001009096 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)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x1
001009096 9141_ $$y2023
001009096 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001009096 920__ $$lyes
001009096 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001009096 980__ $$acontrib
001009096 980__ $$aVDB
001009096 980__ $$aUNRESTRICTED
001009096 980__ $$acontb
001009096 980__ $$aI:(DE-Juel1)JSC-20090406
001009096 9801_ $$aFullTexts