3 papers
cs.LG2022
Mixture of Decision Trees for Interpretable Machine Learning
Simeon Brüggenjürgen, Nina Schaaf, Pascal Kerschke +1
This work introduces a novel interpretable machine learning method called Mixture of Decision Trees (MoDT). It constitutes a special case of the Mixture of Experts ensemble archite…
cs.CV2021
Towards Measuring Bias in Image Classification
Nina Schaaf, Omar de Mitri, Hang Beom Kim +2
Convolutional Neural Networks (CNN) have become de fact state-of-the-art for the main computer vision tasks. However, due to the complex underlying structure their decisions are ha…
cs.LG2019
Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularization
Nina Schaaf, Marco F. Huber, Johannes Maucher
One obstacle that so far prevents the introduction of machine learning models primarily in critical areas is the lack of explainability. In this work, a practicable approach of gai…