Overview
This course provides a broad perspective on Artificial Intelligence (AI), focusing on the foundational principles powering modern AI systems. The curriculum first introduces the mechanisms behind generative AI, including Large Language Models (LLMs) and diffusion models, with a specific emphasis on the underlying optimization techniques that drive learning. We then study core decision-making frameworks: search, reinforcement learning, and game theory to provide a well-rounded understanding of how AI systems reason, plan, and act. The course highlights the connections between these classical techniques and modern advances, particularly in the development of AI agents and inference-time reasoning. We finally touch upon aspects of robustness, safety, and ethical considerations to encourage critical thinking about the role of AI in society. Through a combination of lectures offering a mathematical perspective, hands-on assignments, and discussions, students will explore both theoretical underpinnings and practical implementations.
Pre-requisites
There are no formal pre-requisites for the course, but students should have previous programming experience (programming assignments will be given in Python). Additionally, students are expected to have a strong working knowledge of linear algebra and probability, as these are essential for the technical components of the course. Please see the instructors if you are unsure whether your background is suitable for the course.
Learning resources
There is no official textbook for this class. We will put up lecture slides with pointers to relevant papers and textbook material.