Awesome Explainable Systems

A curated list of awesome research projects, software, and libraries in the area of explainable systems.

A fully Explainable System is a system of which humans can (easily) understand all relevant aspects.

Explaining Black-Box Models

  • Interpretable ML Book — A guide for making black box models explainable.
  • Shap — A unified approach to explain the output of any machine learning model.
  • What-If Tool — Provides an easy-to-use interface for understanding ML models.