Search Results for author: Fabian Hoitsma

Found 2 papers, 1 papers with code

Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps

1 code implementation16 May 2023 Isel Grau, Gonzalo Nápoles, Fabian Hoitsma, Lisa Koutsoviti Koumeri, Koen Vanhoof

In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification.

Fairness Feature Importance

Prolog-based agnostic explanation module for structured pattern classification

no code implementations23 Dec 2021 Gonzalo Nápoles, Fabian Hoitsma, Andreas Knoben, Agnieszka Jastrzebska, Maikel Leon Espinosa

Thirdly, we encode instances as a Prolog rule using the nominal values, the predefined symbols, the decision classes, and the confidence values.

Chatbot Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.