20.500.12556/RUL-161046 Razvoj gradnikov za analizo pristranosti v programu Orange Development of components for bias analysis in Orange Umetna inteligenca in strojno učenje se vse pogosteje uporabljata v procesih odločanja, kot so zaposlovanje, izrekanje kazni na sodiščih ali odobritev posojil. Ker te odločitve pomembno vplivajo na posameznike, modeli odločanja ne smejo biti pristrani do določenih demografskih skupin. V diplomski nalogi smo preizkusili uporabo različnih algoritmov odstranjevanja in odkrivanja pristranosti v podatkih in napovedih modelov. Rezultati kažejo, da so metode, ki smo jih preučevali za zmanjšanje pristranosti, učinkovite in relativno enostavne za uporabo. Glavni rezultat naloge je razširitev za okolje Orange, ki vključuje gradnike za obravnavanje pristranosti. Razvite gradnike lahko uporabljajo tudi posamezniki brez znanja programiranja. Razširitev je prosto dostopna na repozitoriju GitHub (programska koda) in v programskem okolju Orange. O implementaciji smo poročali tudi na spletnih straneh orodja Orange. Artificial intelligence and machine learning are increasingly being used in decision-making processes such as hiring, sentencing, and credit approval. Given the significant impact these decisions have on people's lives, the models that drive them must be free of bias against any demographic group. In this thesis, we tested several algorithms designed to detect and mitigate bias in data and model predictions. The results show that the methods we tested are both effective and relatively easy to use. One of the main results of this work is an add-on developed for the Orange environment to help users without programming skills to address and understand bias in machine learning. This add-on is available on GitHub, where the source code is available, and has been integrated into the Orange programming environment. We reported on the implementation on the Orange tool website. pristranost pravičnost strojno učenje vizualno programiranje Orange bias fairness machine learning visual programming Orange true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2024-09-06 10:50:00 2024-09-06 10:50:07 2024-10-11 11:34:13 0000-00-00 00:00:00 2024 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 37591 211187971 Mervic_Zan_-_Razvoj_gradnikov_za_analizo_pristranosti_v_programu_Orange.pdf Mervic_Zan_-_Razvoj_gradnikov_za_analizo_pristranosti_v_programu_Orange.pdf 1 C1540FACA1B34BEADD064C78D5DF44FD 14298e9c5c274328e6120fda569bd0d2f827347d34f91684b734fefb55425418 ffc78a12-6c2c-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=189903 Fakulteta za računalništvo in informatiko 0 0 0