Fundamentals of Explainability and AI Ethics
Learn how to build more transparent, ethical, and fair AI systems by understanding explainability, bias, and how different AI approaches work together.
Course Information
Certificate Track
About this Course
Build the skills to understand, evaluate, and design trustworthy AI systems. In this course, you’ll learn why explainability matters and how to make sense of model decisions using clear, practical methods. You’ll develop a strong intuition for how different types of models work and how to assess their strengths, limits, and real-world impact.
You’ll begin with the foundations of explainable AI and exploring why transparency matters. Along the way, you’ll examine how bias enters data and models, learn ways to measure fairness, and understand how to balance accuracy with responsible decision-making. By the end of the course, you’ll be able to think critically about how to design and use AI systems that are both effective and trustworthy.
Fundamentals of Explainability and AI Ethics is one of the five courses in Universal AI, a self-paced program designed to help you go from beginner to AI authority—no coding or technical skills required.
What you'll learn
- Understand why explainability is important for building trust in AI systems
- Learn different ways to explain model decisions, including global, local, and counterfactual methods
- Compare simple, interpretable models with more complex models that require post-hoc explanations
- Analyze AI ethical challenges and bias, including the trade-offs of applying different definitions of fairness to predictive systems
- Evaluate the AI alignment problem, exploring techniques to align systems with human preferences while navigating the challenges of conflicting human values
Modules
This course has 3 modules
Meet your instructors
Dimitris Bertsimas
Vice Provost for Open Learning, MIT Open Learning
Dimitris Bertsimas is the Vice Provost for Open Learning at MIT, the Associate Dean of Business Analytics, the Boeing Leaders for Global Operations Professor of Management, and a Professor of Operations Research at MIT Sloan School of Management. At MIT Open Learning, he oversees Open Learning’s product offerings, new initiatives, infrastructure, finances, and operations.
