Search
Lectures: Petr Pošík, Tomas Svoboda
Labs: Swati Dantu
The course introduces the students to the field of artificial intelligence and gives the necessary basis for designing machine control algorithms. It advances the knowledge of state space search algorithms by including uncertainty in state transitions. Students are introduced into reinforcement learning for solving problems when the state transitions are unknown. Bayesian decision task introduces supervised learning. Learning from data is demonstrated on a linear classifier. Students practice the algorithms in computer labs.
Prerequisities: The course expects basic knowledge of probability and linear algebra. We expect that students are able to write decent computer programs in a higher level language and have basic knowledge of data structures. Python will be used in computer labs.
The course runs in a hybrid regime. The lectures and lab sessions for online participants are streamed and recorded via BigBlueButton in BRUTE. Students enrolled in EECS or other regular presence study programs at CTU are expected to physically attend lectures/labs.
The final assesment will be composed of thee components: lab assignments, mid-term exam, and final exam.
45 points for homework (assignments during comp. labs)
Note: There will be some bonus points for discussions/quizzes during the computer labs.
The final exam is worth 40 points. You need at least 18 points from the final exam to pass.
Note that that you will need to fulfil the criteria specified above - collect points for assignments during the semester. Otherwise, you will not be allowed to take the final exam.
It will be a written exam, lasting 120 min. No books or notes will be allowed. The necessary formulas will be provided. The questions will be rather practical - you will be asked to solve (calculate) particular problems, similar to those during the lectures and labs.
Exam dates:
F means fail.