Model Agnostics breakDown plots
The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learn...
ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image ...
Break Down with interactions for local explanations (SHAP, BreakDown, iB...
Compute SHAP values for your tree-based models using the TreeSHAP algorithm
Modular Python Toolbox for Fairness, Accountability and Transparency For...
A user interface to interpret machine learning models.
Text classification models. Used a submodule for other projects.
Adversarial Attacks on Post Hoc Explanation Techniques (LIME/SHAP)
Automatic equation building and curve fitting. Runs on Tensorflow. Built...
Adaptive, interpretable wavelets across domains (NeurIPS 2021)
Interesting resources related to Explainable Artificial Intelligence, In...
code release for Representer point Selection for Explaining Deep Neural ...
BayesGrad: Explaining Predictions of Graph Convolutional Networks
General Interpretability Package