AI 413 - Explainability & Minimal Fairness in Engineering

This course explores the foundational principles of model explainability and fairness in machine learning, focusing on tools and techniques that enhance model transparency while maintaining essential fairness standards. This course introduces students to key explainability frameworks such as LIME, SHAP, and others within Python-based environments, helping students design and implement machine learning models that are not only technically efficient but also interpretable and fair. Through practical, hands-on experience, students will learn to balance the trade-offs between transparency and performance, developing models that offer both clarity and minimal bias.

Credits: 3

Class Level Senior Undergraduate
Program Undergraduate