Vis enkel innførsel

dc.contributor.authorHufthammer, Knut T.
dc.contributor.authorAasheim, Tor H.
dc.contributor.authorÅnneland, Sølve
dc.contributor.authorBrynjulfsen, Håvard
dc.contributor.authorSlavkovik, Marija
dc.date.accessioned2021-07-13T07:55:29Z
dc.date.available2021-07-13T07:55:29Z
dc.date.created2020-12-15T11:14:28Z
dc.date.issued2020
dc.identifier.isbn978-3-540-68164-9
dc.identifier.issn1892-0713
dc.identifier.urihttps://hdl.handle.net/11250/2764230
dc.description.abstractThe use of artificial intelligence for decision making raises concerns about the societal impact of such systems. Traditionally, the product of a human decision-maker are governed by laws and human values. Decision-making is now being guided - or in some cases, replaced by machine learning classification which may reinforce and introduce bias. Algorithmic bias mitigation is explored as an approach to avoid this, however it does come at a cost: efficiency and accuracy. We conduct an empirical analysis of two off-the-shelf bias mitigation techniques from the AIF360 toolkit on a binary classification task. Our preliminary results indicate that bias mitigation is a feasible approach to ensuring group fairness.en_US
dc.language.isoengen_US
dc.publisherNorsk IKT-konferanse for forskning og utdanningen_US
dc.relation.ispartofNIKT: Norsk IKT-konferanse for forskning og utdanning 2020
dc.titleBias mitigation with AIF360: A comparative studyen_US
dc.typeChapteren_US
dc.description.versionpublishedVersionen_US
cristin.ispublishedtrue
cristin.fulltextoriginal
dc.identifier.cristin1859922
dc.identifier.citationNIK Norsk informatikkonferanse. 2020, 1.en_US


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel