This course offers a broad introduction to the fundamental concepts, techniques and applications of artificial intelligence. We begin by exploring uninformed and informed search strategies, constraint‐satisfaction and adversarial search, then move into probabilistic reasoning—covering uncertainty, Bayesian networks and their extensions. Then, we delve into machine learning methods (decision trees, linear models, Bayesian learning and deep learning) and decision theory. The latter half of the term focuses on sequential decision making, introducing Markov models and Markov decision processes before examining reinforcement learning and its multi‐agent variants.
| Item | Undergraduate | Graduate |
|---|---|---|
| 4 Assignments | 36% | 28% |
| Midterm | 20% | 16% |
| Final | 40% | 36% |
| Participation | 4% | 4% |
| Project | not applicable | 16% |
This course is not something where you can easily get by with minimal effort or rely on tools like GPT to do the work for you. This class covers classical AI as well as new developments in AI. It involves both theoretical understanding (e.g. Bayesian networks, inference) as well as programming (e.g. implementing search, reinforcement learning). In addition to assignments, you will be assessed via closed-book, in-person midterm and final exams.
This is also a new iteration of the class, consequently please expect to run into bugs as we iron out details for this new iteration!
All late submissions are handled through official Short Term Absences and Verification of Illness. Late days are not granted outside of official STA/VIF channels.