The goal of this course is to introduce students to explainable AI (XAI) methods, which aim to explain the predictions of black-box AI models. Such explanations are important for establishing good communication, trust, clarity, and understanding of AI models, which can increase their adoption in critical systems and for solving complex problems. This course is intended to give a broad overview of different XAI methods from a practical standpoint, with a focus on applying XAI and interpreting and analyzing the AI systems. At the end of the course, students will have both working knowledge of and practical experience implementing and applying XAI on different AI models and different domains.

Continuous Assessment: 70%

Examination: 30%

Examination Duration: 2 hours

Min. Examination Passing Requirement: 30%

For a student to pass the course, at least 30% of the maximum mark for the examination AND course project must be obtained.