Lectures

Lectures will be delivered by Matej Hoffmann or Tomas Svoboda (TS).

PDF of the slides will be posted on this page. Note, however, that lectures will contain a significant portion of blackboard writing as well as some live programming pieces. Reading/watching slides only is not enough. Active participation in lectures is welcomed and encouraged.

Current tentative schedule is right below. For the time being, the schedule from last year with links to slides is kept further down.

date week nr. content
18.02.2019 1 Rules of the game (grading, assignments, etc.). Cybernetics and AI - motivation. Goal-directed machine. Is every problem solvable? 01_intro_mh_2019_v1.0_ekui_compressed.pdf
25.02.2019 2 Solving problems by search. Trees and graphs. Completeness, Optimality, Complexity. DFS, BFS. 02_search.pdf
04.03.2019 3 Solving problems by search. How to avoid looping forever and how to go faster to the goal. Informed search. Heuristics. A*. 03_search.pdf
11.03.2019 4 Two player-games. Adversarial search - Search when playing against a (rational) opponent. 04_adversarial.pdf (TS)
18.03.2019 5 Games with random elements, multi-player games. Expectimax. Utilities. 05_expectimax_withnotes.pdf
25.03.2019 6 Decision-making under uncertainty I. Route to goal when action outcome is probabilistic. Value iteration. 06_mdp_withnotes.pdf
01.04.2019 7 Decision-making under uncertainty II. Policy iteration. 07_mdp_withnotes.pdf
08.04.2019 8 Reinforcement learning. What if nothing is known about the probability of action outcomes and we have to learn from final success or failure? (TS) 08_rl.pdf
15.04.2019 9 Reinforcement learning II. 09_rl_withnotes.pdf
22.04.2019 10 Holiday - Easter Monday
29.04.2019 11 Mid-term exam from topics covered up to now - inspiration: quizzes.
06.05.2019 12 Bayesian classification and decisions. 10_bayes_withnotes.pdf
13.05.2019 13 Bayesian classification, ROC characteristics, k-nn and relationship to Bayesian classifier. 11_recog_a_withnotes.pdf 11_recog_b_withnotes.pdf
20.05.2019 14 Classification in feature space. Discriminant functions. Linear separability. Nearest neighbor classification. Perceptron algorithm. 11_recog_b_withnotes.pdf. Maximum likelihood estimation - very brief intro (15 min.), not for exam.
courses/be5b33kui/lectures/start.txt · Last modified: 2019/05/20 12:33 by hoffmmat