Interpretable Ml

Interpretable machine learning, model explainability, and XAI

NeuralBlitz Updated 3 repo stars

File contents

What I do

  • Build interpretable models
  • Explain black-box models
  • Apply SHAP and LIME
  • Visualize model decisions

When to use me

When building explainable AI or interpreting ML models.

Key Concepts

  • SHAP values
  • LIME
  • Feature importance
  • Partial dependence
  • Counterfactuals
  • Interpretable models
  • Model-agnostic methods

neuralblitz/mito commit fa43a4f65f

Frequently asked questions

npx get-skill add neuralblitz/interpretable-ml