Sökning: "förklarbara förutsägelser"

Hittade 2 uppsatser innehållade orden förklarbara förutsägelser.

  1. 1. Explainability Methods for Transformer-based Artificial Neural Networks: : a Comparative Analysis

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Eliott Remmer; [2022]
    Nyckelord :XAI; NLP; Transformers; BERT; explainable predictions; SHAP; Attention; XAI; NLP; Transformers; BERT; förklarbara förutsägelser; SHAP; Attention;

    Sammanfattning : The increasing complexity of Artificial Intelligence (AI) models is accompanied by an increase in difficulty in interpreting model predictions. This thesis work provides insights and understanding of the differences and similarities between explainability methods for AI models. LÄS MER

  3. 2. Leveraging Explainable Machine Learning to Raise Awareness among Preadolescents about Gender Bias in Supervised Learning

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Gaspar Isaac Melsion Perez; [2020]
    Nyckelord :explainable AI; interpretability; education; children; gender; bias; machine learning; human-computer interaction; förklarbar AI; tolkbarhet; utbildning; barn; kön; bias; maskininlärning; människa-datorinteraktion;

    Sammanfattning : Machine learning systems have become ubiquitous into our society. This has raised concerns about the potential discrimination that these systems might exert due to unconscious bias present in the data, for example regarding gender and race. LÄS MER