Lectures

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

PDF of the slides will be posted on this page. Preliminary version (e.g., last year's) before the lecture. Latest version, including teacher's notes shortly after the lecture. If you spot mistakes in the slides, please report them. Important corrections may be rewarded with bonus points. Note, however, that the 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.

Books, on-line resources, specialization courses will be referenced throughout the lectures - typically from the last lecture slide.

The schedule will be frequently updated, in particular taking into account FEE Covid19 info. The lectures switch to the Distance teaching mode from March 23, 2020.

date week nr. content
17.02.2020 1 Rules of the game (grading, assignments, etc.). Cybernetics and AI - motivation. Course overview. Is every problem solvable? N-puzzle. 01_intro_mh_2020_v5_novideos.pdf
24.02.2020 2 Solving problems by search. Trees and graphs. Completeness, Optimality, Complexity. DFS, BFS. 02_search_withnotes.pdf
02.03.2020 3 Solving problems by search. How to avoid looping forever and how to go faster to the goal. Informed search. Heuristics. A*. 03_search_live_withnotes.pdf
09.03.2020 4 Two player-games. Adversarial search - Search when playing against a (rational) opponent. 04_adversarial_withnotes.pdf
16.03.2020 23.3.2020 watch on-line 5 Games with random elements, multi-player games. Expectimax. Utilities. Please watch online video: AI@Berkeley and study lecture slides with notes 05_expectimax_withnotes.pdf.
30.03.2020 watch online 6 Decision-making under uncertainty I. Route to goal when action outcome is probabilistic. Value iteration. Please watch online video: AI@Berkeley and study lecture slides with notes 06_mdp_withnotes.pdf
06.04.2020 watch online 7 Decision-making under uncertainty II. Policy iteration. Please watch online video: AI@Berkeley and study lecture slides with notes 07_mdp_withnotes.pdf
13.04.2020 8 Holiday - Easter Monday
20.04.2020 watch online 9 Reinforcement learning. What if nothing is known about the probability of action outcomes and we have to learn from final success or failure? Please watch online video: AI@Berkeley and study lecture slides with notes 08_rl_live_withnotes.pdf
27.04.2020 watch online 10 Reinforcement learning II. Exploration vs. exploitation. Please watch online video: AI@Berkeley and study lecture slides with notes 09_rl_withnotes.pdf
04.05.2020 online 11 Mid-term exam from topics covered up to now. Inspiration: quizzes.
11.05.2020 online 12 Bayesian classification and decisions. 10_bayes.pdf 10_bayes_live_withnotes.pdf BBB recording
18.05.2020 watch online 13 Naive Bayesian classification, Laplace smoothing, Precision, Recall and ROC curve. Please watch online video AI@Berkeley: Naive Bayes and Laplace smoothing, study Precision, Recall and ROC curve (or this video by Andrew Ng) or consult lecture slides with notes 11_recog_a_live_withnotes.pdf.
25.05.2020 watch online 14 Linear classifiers, perceptron (watch AI@Berkeley: Perceptrons). Nearest neighbor (k-nn) classification (watch AI@Berkeley: Machine Learning: Kernels and Clustering - only up to min. 16). Consult lecture slides with notes 11_recog_b_withnotes.pdf.
courses/be5b33kui/lectures/start.txt · Last modified: 2020/05/21 16:50 by hoffmmat