001033583 001__ 1033583
001033583 005__ 20251217202222.0
001033583 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-06463
001033583 037__ $$aFZJ-2024-06463
001033583 041__ $$aEnglish
001033583 1001_ $$0P:(DE-Juel1)199019$$aCao, Zhuo$$b0$$ufzj
001033583 245__ $$aGalaxy Morphology Classification with Counterfactual Explanation
001033583 260__ $$c2024
001033583 3367_ $$2DataCite$$aText
001033583 3367_ $$0PUB:(DE-HGF)20$$2PUB:(DE-HGF)$$aMinutes$$bminutes$$mminutes$$s1765959395_26386
001033583 3367_ $$2BibTeX$$aMISC
001033583 3367_ $$2ORCID$$aOTHER
001033583 3367_ $$2DINI$$aOther
001033583 3367_ $$04$$2EndNote$$aPersonal Communication
001033583 520__ $$aGalaxy morphologies play an essential role in the study of the evolution of galaxies. The determination of morphologies is laborious for a large amount of data giving rise to machine learning-based approaches. Unfortunately, most of these approaches offer no insight into how the model works and make the results difficult to understand and explain. We here propose to extend a classical encoder-decoder architecture with invertible flow, allowing us to not only obtain a good predictive performance but also provide additional information about the decision process with counterfactual explanations.
001033583 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001033583 65027 $$0V:(DE-MLZ)SciArea-250$$2V:(DE-HGF)$$aOthers$$x0
001033583 7001_ $$0P:(DE-Juel1)196726$$aKrieger, Lena$$b1$$ufzj
001033583 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b2$$ufzj
001033583 7001_ $$0P:(DE-Juel1)188313$$aAssent, Ira$$b3$$ufzj
001033583 8564_ $$uhttps://juser.fz-juelich.de/record/1033583/files/Counterfactuals_Galaxy_JUSER.pdf$$yOpenAccess
001033583 909CO $$ooai:juser.fz-juelich.de:1033583$$popenaire$$popen_access$$pVDB$$pdriver
001033583 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)199019$$aForschungszentrum Jülich$$b0$$kFZJ
001033583 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)196726$$aForschungszentrum Jülich$$b1$$kFZJ
001033583 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b2$$kFZJ
001033583 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188313$$aForschungszentrum Jülich$$b3$$kFZJ
001033583 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$$x0
001033583 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001033583 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001033583 9801_ $$aFullTexts
001033583 980__ $$aminutes
001033583 980__ $$aVDB
001033583 980__ $$aUNRESTRICTED
001033583 980__ $$aI:(DE-Juel1)IAS-8-20210421