Sökning: "Klaus Virtanen"

Hittade 1 uppsats innehållade orden Klaus Virtanen.

  1. 1. Using XAI Tools to Detect Harmful Bias in ML Models

    Kandidat-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Klaus Virtanen; [2022]
    Nyckelord :Explainable AI; XAI; Machine Learning; Bias; Bias in Machine Learning; LIME; SHAP;

    Sammanfattning : In the past decade, machine learning (ML) models have become farmore powerful, and are increasingly being used in many important contexts. At the same time, ML models have become more complex, and harder to understand on their own, which has necessitated an interesting explainable AI (XAI), a field concerned with ensuring that ML and other AI system can be understood by human users and practitioners. LÄS MER