Responsible Artificial Intelligence
This course introduces the fundamental concepts, challenges, and methods of Responsible Artificial Intelligence (Responsible AI). The first part of the course focuses on the foundations of Responsible AI, including bias, fairness, explainability, robustness, reliability, and privacy in AI systems. The second part of the course focuses on methods and techniques for responsible AI design, with particular emphasis on bias and fairness in machine learning, explainable AI (XAI), and adversarial robustness. By the end of the course, students will have learned how to identify, analyze, and evaluate biases in AI systems, apply methods for explaining model behavior, and systematically incorporate fairness, explainability, and robustness aspects into the design and application of AI systems.
Course content:
(Topics may be adjusted slightly during the trimester)
- Foundations of Responsible/Trustworthy AI
- Bias in AI Systems
- Fairness-Aware Learning
- Explainable AI (XAI)
- Adversarial Robustness
Literature:
- Virginia Dignum, Responsible Artificial Intelligence - How to Develop and Use AI in a Responsible Way, Springer, 2019.
- Solon Barocas, Moritz Hardt, Arvind Narayanan, Fairness and Machine Learning: Limitations and Opportunities, online, 2022.
- Christopher Molnar, Interpretable Machine Learning - A Guide for Making Black Box Models Explainable, online, 2022.