Explainable Al (XAI) with Python

Course content

  • Introduction to XAI
  • Demonstration of By Design Interpretable Models: Glass
  • Box
  • LIME (Local Interpretable Model Agnostic Explanations)
  • SHAP (SHapIey Additive exPIanations)
  • Counterfactual Explanations
  • Google’s What-if Tool (WIT) for A1 fairness and Counterfactuals
  • Layer-wise Relevance Propagation (LRP)
  • Contrastive Explanations Method (CEM)
  • Useful Resources for XAI
  • Final Quiz
  • Surprise on Completion of Course
  • Other resources from the Instructor
  • Acknowledgement