Contents

• Limitations of Interpretability
• NeurIPS 2019 Interpretability Roundup
• Interpretability by Design
• Reinforcement Learning for NLP and Text
• Tutorials and Introductory remarks
• Concept-based Explanations

Resources

Tutorials

Title	Venue	Authors	slides
Interpretable ML: The fuss, the concrete and the questions	ICML 2017	Kim and Doshi-Velez	link
Tutorial on XKDD	XKDD Workshop ECML 2018	Monreale et al.	link
Explainable AI in Industry	KDD 2019	Geyik et al., LinkedIn	link
On Explainable AI:From Theory to Motivation, Applications and Limitations	AAAI 2019	many	link

Overviews, Surveys, Reviews

Title	Author	link
The Mythos of Model Interpretability	Lipton	arxiv
Towards a Rigorous Science of Interpretable Machine Learning	Doshi-Velez and Kim	arxiv
A Survey of Methods for Explaining Black Box Models	Guidotti et al.	arxiv
Interpretability of Machine Learning Models and Representations: an Introduction	Adrien Bibal and Benoît Frénay	pdf

Books

Title	Author	link
Interpretable ML: A Guide for Making Black Box Models Explainable.	Molnar	link
Limitations of Interpretable Machine Learning Methods	LMU seminar	link

Editing & browsing this wiki locally using vscode:

• clone wiki:

  git clone git@git.l3s.uni-hannover.de:anand/interpretability.wiki.git
  cd interpretability.wiki

• install vscode extension yzhang.markdown-all-in-one
• install vscode extension goessner.mdmath
• go to user settings, search for mdmath and set Delimiters to 'gitlab'
• The vscode markdown preview should now render according to the gitlab markdown standard
• commit and push changes using git
• images can be put into the uploads folder and refered to as ./uploads/image.png