000910149 001__ 910149
000910149 005__ 20230502100726.0
000910149 0247_ $$2doi$$a10.1109/IGARSS46834.2022.9883257
000910149 0247_ $$2Handle$$a2128/32035
000910149 0247_ $$2WOS$$aWOS:000920916600066
000910149 037__ $$aFZJ-2022-03638
000910149 041__ $$aEnglish
000910149 1001_ $$0P:(DE-Juel1)180916$$aAach, Marcel$$b0$$eCorresponding author$$ufzj
000910149 1112_ $$a2022 IEEE International Geoscience and Remote Sensing Symposium$$cKuala Lumpur$$d2022-07-17 - 2022-07-22$$gIGARSS 2022$$wMalaysia
000910149 245__ $$aAccelerating Hyperparameter Tuning of a Deep Learning Model for Remote Sensing Image Classification
000910149 260__ $$bIEEE$$c2022
000910149 300__ $$a263-266
000910149 3367_ $$2ORCID$$aCONFERENCE_PAPER
000910149 3367_ $$033$$2EndNote$$aConference Paper
000910149 3367_ $$2BibTeX$$aINPROCEEDINGS
000910149 3367_ $$2DRIVER$$aconferenceObject
000910149 3367_ $$2DataCite$$aOutput Types/Conference Paper
000910149 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1666007802_30576
000910149 520__ $$aDeep Learning models have proven necessary in dealing with the challenges posed by the continuous growth of data volume acquired from satellites and the increasing complexity of new Remote Sensing applications. To obtain the best performance from such models, it is necessary to fine-tune their hyperparameters. Since the models might have massive amounts of parameters that need to be tuned, this process requires many computational resources. In this work, a method to accelerate hyperparameter optimization on a High-Performance Computing system is proposed. The data batch size is increased during the training, leading to a more efficient execution on Graphics Processing Units. The experimental results confirm that this method reduces the runtime of the hyperparameter optimization step by a factor of 3 while achieving the same validation accuracy as a standard training procedure with a fixed batch size.
000910149 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000910149 536__ $$0G:(EU-Grant)951733$$aRAISE - Research on AI- and Simulation-Based Engineering at Exascale (951733)$$c951733$$fH2020-INFRAEDI-2019-1$$x1
000910149 536__ $$0G:(DE-Juel1)PHD-NO-GRANT-20170405$$aPhD no Grant - Doktorand ohne besondere Förderung (PHD-NO-GRANT-20170405)$$cPHD-NO-GRANT-20170405$$x2
000910149 588__ $$aDataset connected to CrossRef Conference
000910149 7001_ $$0P:(DE-Juel1)178695$$aSedona, Rocco$$b1$$ufzj
000910149 7001_ $$0P:(DE-Juel1)165948$$aLintermann, Andreas$$b2$$ufzj
000910149 7001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b3$$ufzj
000910149 7001_ $$0P:(DE-HGF)0$$aNeukirchen, Helmut$$b4
000910149 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b5$$ufzj
000910149 773__ $$a10.1109/IGARSS46834.2022.9883257
000910149 8564_ $$uhttps://juser.fz-juelich.de/record/910149/files/IGARSS2022_Aach_et_al.pdf$$yOpenAccess
000910149 909CO $$ooai:juser.fz-juelich.de:910149$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
000910149 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180916$$aForschungszentrum Jülich$$b0$$kFZJ
000910149 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178695$$aForschungszentrum Jülich$$b1$$kFZJ
000910149 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165948$$aForschungszentrum Jülich$$b2$$kFZJ
000910149 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b3$$kFZJ
000910149 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b5$$kFZJ
000910149 9131_ $$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
000910149 9141_ $$y2022
000910149 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000910149 920__ $$lyes
000910149 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000910149 980__ $$acontrib
000910149 980__ $$aVDB
000910149 980__ $$aUNRESTRICTED
000910149 980__ $$aI:(DE-Juel1)JSC-20090406
000910149 9801_ $$aFullTexts