Andraž Pirnovar: Interpretable machine learning - an introduction

V četrtek, 12. 9. 2024, ob 14:15 bo v predavalnici 3.06 v okviru seminarja VeSFiM potekalo predavanje Andraža Pirnovarja z naslovom Interpretable machine learning - an introduction.

Povzetek: In the quest for improved performance, increasingly complex machine learning models are being developed. However, understanding the why can be just as important as the prediction itself. Complex models often lack inherent explainability, making them difficult to interpret. I will present the need for interpretability methods and introduce key concepts behind them. As a practical example, the focus will be on the LIME algorithm, which will be used on a loan default dataset.

Predavanje bo potekalo v živo, bo pa omogočen tudi prenos prek interneta. Povezava na videokonferenčni sistem ZOOM: https://uni-lj-si.zoom.us/j/95492285750 ID: 954 9228 5750

Vljudno vabljeni!