This repository provides the materials for the methods week in Statistics on the topic "Interpretable Machine Learning".
The repository is structured as follows:
- exercises: exercise sheet (Exercise.pdf) for the practical part of the methods week & exercise sheet (exercises-wine) with (the same) questions transfered to the wine dataset (including solutions)
- slides: slides for the theoretical part of the methods week partitioned
Note: The HTML file can be previewed in your browser with this link within github.
- Chen H, Janizek JD, Lundberg S, Lee SI (2020). True to the model or true to the data? ICML Workshop on Human Interpretability 2020. https://arxiv.org/abs/2006.16234
- Grinsztajn L, Oyallon E, Varoquaux G (2022). Why do tree-based models still outperform deep learning on typical tabular data? NeurIPS 2022. https://openreview.net/pdf?id=Fp7__phQszn
- Au Q, Herbinger J, Stachl C, Bischl B, Casalicchio G (2022). Grouped feature importance and combined features effect plot. Data Mining and Knowledge Discovery 36:1401-50. https://doi.org/10.1007/s10618-022-00840-5
- survex: Explainable Machine Learning in Survival Analysis. https://github.com/ModelOriented/survex (also on CRAN)
- Molnar C, König G, Herbinger J, Freiesleben T, Dandl S, Scholbeck CA, Casalicchio G, Grosse-Wentrup M, Bischl B (2022). General pitfalls of model-agnostic interpretation methods for machine learning models. ICML 2020 Workshop Beyond Explainable AI. https://doi.org/10.1007/978-3-031-04083-2_4