Model Interpretability (XAI)

Learning Objectives

•Global vs. Local Interpretability
•SHAP (SHapley Additive exPlanations)
•LIME (Local Interpretable Model-agnostic Explanations)
•Feature Importance (Permutation Importance, Partial Dependence Plots)
•Fairness and Bias in AI

Weekly Outcome

By the end of this module you will be able to interpret complex machine learning models, ensure fairness and transparency, and apply scalable data engineering techniques for processing and analyzing large datasets.

Resources

Data skill learning paths | DataCamp NVIDIA garak Tutorial: Build a Complete Defensive LLM Microsoft Fara Tutorial: Run a Browser-Use Agent in Google