Artificial Intelligence has grown powerful, but often functions as a “black box.” This course on Explainable AI (XAI) is designed to help you understand, interpret, and trust AI systems by uncovering how models make their decisions.

You’ll start with the foundations of XAI—why model interpretability matters, the challenges involved, and the role of explainability in building responsible AI. From there, the course takes a hands-on approach, guiding you through two of the most widely used techniques: SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations).

Key learning highlights include:

• Understanding SHAP: installation, code, background data effects, and visualizations
• Applying SHAP to regression, classification, and deep learning models (ANN & CNN)
• Exploring global and local interpretations using plots, heatmaps, and force diagrams
• Learning the mathematical foundations of Shapley values from game theory
• Comparing SHAP and LIME, with practical case studies on both regression and classification tasks

By the end of this course, you’ll be able to explain model predictions with confidence, use visual interpretations to communicate insights, and evaluate AI systems more responsibly.

Course Duration: 17+ hours