mmschlk/shapiq

A game theoretic approach to explain the output of any machine learning model.

Explaining the output of machine learning models with more accurately estimated Shapley values

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

For calculating global feature importance using Shapley values.

Lime: Explaining the predictions of any machine learning classifier

Interpretability and explainability of data and machine learning models

Fit interpretable models. Explain blackbox machine learning.

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

Model interpretability and understanding for PyTorch