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.
(w-week number; Odd/Even teaching week)
| date | w | O/E | content |
|---|---|---|---|
| 19.02.2018 | 1. | E | Rules of the game (grading, assignments, etc.). Introduction to (Objective) Python. We will design Rock-Paper-Scissors implementation. (TS) rock-paper-scissors.pdf |
| 26.02.2018 | 2. | O | Cybernetics and AI - motivation. Goal-directed machine. Is every problem solvable? kui-01-intro.pdf |
| 05.03.2018 | 3. | E | Solving problems by search. Trees and graphs. How to avoid getting stuck in dead ends. 02_search.pdf(TS) |
| 12.03.2018 | 4. | O | Solving problems by search. How to avoid looping forever and how to go faster to the goal. Informed search. Heuristics. 03_search.pdf |
| 19.03.2018 | 5. | E | Two player-games. Adversarial search - Search when playing against a (rational) opponent. (TS) 04_adversarial.pdf |
| 26.03.2018 | 6. | O | Games with random elements, multi-player games. Expectimax. 05_expectimax.pdf |
| 02.04.2018 | 7. | E | Easter - holiday, no teaching |
| 09.04.2018 | 8. | O | Decision-making under uncertainty I. Route to goal when action outcome is probabilistic. Value iteration. 06_mdp.pdf |
| 16.04.2018 | 9. | E | Decision-making under uncertainty II. Policy iteration. 07_mdp_mh.pdf |
| 23.04.2018 | 10. | O | 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 |
| 30.04.2018 | 11. | E | Mid-term exam from topics covered up to now - inspiration: quizzes. Lecture: Bayesian classification and decisions. 10_bayes.pdf |
| 07.05.2018 | 12. | O | Bayesian classification and decisions. 10_bayes.pdf (TS) |
| 14.05.2018 | 13. | E | Classification - Perceptron, k-nn and relationship to Bayesian classifier. 11_recog.pdf |
| 21.05.2018 | 14. | O | Learning probabilistic models from data - Maximum Likelihood (ML) estimation 12_mle.pdf. Additional resources: matas_pr_03_parameter_estimation_2016_10_17.pdf |