Special Topics in Information Science: Explainable Artificial Intelligence

Introduction to Explainable AI through practical applications and real-world examples. Students will gain a basic proficiency in implementing Explainer Algorithms to explain the decisions of ML and AI systems, as well as interpreting the results in a transparent and understandable manner to a non-technical audience. The course will focus on Post-Hoc Explainability techniques and algorithms, including Feature Attribution, Rule-Based and Counterfactuals. Another focus area will be on evaluating the performance of explainability techniques, and understanding the trade-offs associated with various methods. This course is geared towards students interested in a hands-on approach to developing explanations for black-box ML and AI Systems.