Logo des Repositoriums
 

Shifting Quality Assurance of Machine Learning Algorithms to Live Systems

Kurzanzeige
dc.contributor.authorAuer, Florian
dc.contributor.authorFelderer, Michael
dc.contributor.editorTichy, Matthias
dc.contributor.editorBodden, Eric
dc.contributor.editorKuhrmann, Marco
dc.contributor.editorWagner, Stefan
dc.contributor.editorSteghöfer, Jan-Philipp
dc.date.accessioned2019-03-29T10:24:15Z
dc.date.available2019-03-29T10:24:15Z
dc.date.issued2018
dc.description.abstractA fundamental weakness of existing solutions to assess the quality of machine learning algorithms is the assumption that test environments sufficiently mimic the later application. Given the data dependent behavior of these algorithms, only limited reasoning about their later performance is possible. Thus, meaningful quality assurance is not possible with test environments. A shift from the traditional testing environment to the live system is needed. Thus, costly test environments are replaced with available live systems that constantly execute the algorithm.en
dc.identifier.isbn978-3-88579-673-2
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/21162
dc.language.isoen
dc.publisherGesellschaft für Informatik
dc.relation.ispartofSoftware Engineering und Software Management 2018
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-279
dc.subjectmachine learning
dc.subjectquality assurance
dc.subjectlive experimentation
dc.titleShifting Quality Assurance of Machine Learning Algorithms to Live Systemsen
dc.typeText/Conference Paper
gi.citation.endPage212
gi.citation.publisherPlaceBonn
gi.citation.startPage211
gi.conference.date5.-9. März 2018
gi.conference.locationUlm
gi.conference.sessiontitleSoftware Management 2018 - Wissenschaftliches Hauptprogramm

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
B1-64.pdf
Größe:
47.41 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P279 - Software Engineering und Software Management 2018