====== Lectures ====== Lectures are delivered by [[https://sites.google.com/site/matejhof/|Matej Hoffmann]] or [[http://cmp.felk.cvut.cz/~svoboda|Tomas Svoboda (TS)]]. **[[courses:be5b33kui:distance_teaching|Distance teaching]]** The lectures start in the [[https://cw.fel.cvut.cz/wiki/courses/be5b33kui/distance_teaching|Distance teaching mode]] and continue so until we receive other instructions, taking into account [[https://www.fel.cvut.cz/en/covid/|FEE Covid19 info]]. On-line teaching (in real time) and discussion will be using [[http://bigbluebutton.org|BigBlueButton.org]]. You will be invited to every session by email. You can also find the link to the course on [[https://cw.felk.cvut.cz/brute/|BRUTE]], on Course => Conference rooms. Within the BRUTE you will also see recordings in several formats: * Internal viewer - full recording includes slides or shared screen, video streams, and chat. Please note the playing may not work in Safari properly, use other browsers. Video stream and slide screen can be interchanged. * MP4 - video rendered from slide screen or shared screen * PDF - pdf with all drawings made during the on-line session. You can also watch the MP4 recordings at the [[https://youtube.com/playlist?list=PLhGZ28DZufNoCmaLlURGOwN2vUo2ARcZb|BE5B33KUI YouTube]] channel Unless otherwise specified, on-line teaching (lectures/labs) will take place at the times specified in the timetable (same as for standard physical mode). However, often, you will be asked to watch an online lecture from [[http://ai.berkeley.edu/lecture_videos.html|Intro to AI - course from UC Berkeley]] prior to the online lecture. The lecture will then serve to recapitulate and discuss the topics. 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. Active participation in lectures is welcomed and encouraged. [[courses:be5b33kui:literature|Books, on-line resources, specialization courses]] will be referenced throughout the lectures - typically from the last lecture slide. ^ date ^ week nr. ^ content ^ | 15.02.2021 on-line | 1 | Rules of the game (grading, assignments, etc.). Cybernetics and AI - motivation. Course overview. Is every problem solvable? N-puzzle. {{ :courses:be5b33kui:lectures:01_intro.pdf |}} | | 22.02.2021 on-line | 2 | Solving problems by search. Trees and graphs. Completeness, Optimality, Complexity. DFS, BFS. {{ :courses:be5b33kui:lectures:02_search.pdf |}}, {{ :courses:be5b33kui:lectures:02_search_handout_notes.pdf |}} | | 01.03.2021 online | 3 | Solving problems by search. How to avoid looping forever and how to go faster to the goal. Informed search. Heuristics. A*. {{ :courses:be5b33kui:lectures:03_search.pdf |}} {{ :courses:be5b33kui:lectures:03_search_live_withnotes.pdf |}}| | 08.03.2021 online | 4 | Two player-games. Adversarial search - Search when playing against a (rational) opponent. **Watch** [[https://youtu.be/cwbjLIahbv8|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|6 - Adversarial search, AI@Berkeley]] **prior to lecture.** Our slides: {{ :courses:be5b33kui:lectures:04_adversarial.pdf |}} {{ :courses:be5b33kui:lectures:04_adversarial_live_withnotes.pdf |}} .| | 15.03.2021 online | 5 | Games with random elements, multi-player games. Expectimax. Utilities. **Watch** [[https://youtu.be/GevK0-9n24g|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|7 - Expectimax and Utilities, AI@Berkeley]] **prior to lecture.** {{ :courses:be5b33kui:lectures:05_expectimax.pdf |}} {{ :courses:be5b33kui:lectures:05_expectimax_live_withnotes.pdf |}} | | 22.03.2021 online | 6 | Decision-making under uncertainty I. Route to goal when action outcome is probabilistic. Value iteration. **Watch** [[https://youtu.be/wKx4MuLfe0M|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|8 - Markov decision processes I, AI@Berkeley]] **prior to lecture.** {{ :courses:be5b33kui:lectures:06_mdp.pdf |}} {{ :courses:be5b33kui:lectures:06_mdp_live_withnotes.pdf |}} | | 29.03.2021 online | 7 | Decision-making under uncertainty II. Policy iteration. **Watch** [[https://youtu.be/2M7mv4-BPCg|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|9 - Markov decision processes II, AI@Berkeley]] **prior to lecture.** {{ :courses:be5b33kui:lectures:07_mdp.pdf |}} {{ :courses:be5b33kui:lectures:07_mdp_live_withnotes.pdf |}} | | 5.04.2021 | | Holiday - Easter Monday| | 12.04.2021 online | 8 | Reinforcement learning I. What if nothing is known about the probability of action outcomes and we have to learn from final success or failure? **Watch** [[https://youtu.be/hsz0zq6AXGE|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|10 - Reiforcement learning I, AI@Berkeley]] **prior to lecture.** {{ :courses:be5b33kui:lectures:08_rl.pdf |}} {{ :courses:be5b33kui:lectures:08_rl_live_withnotes.pdf |}} | | 19.04.2021 online | 9 | Reinforcement learning II. Exploration vs. exploitation. **Watch** [[https://youtu.be/R0vTZp0ve4s|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|11 - Reiforcement learning II, AI@Berkeley]] **prior to lecture.** {{ :courses:be5b33kui:lectures:09_rl.pdf |}} {{ :courses:be5b33kui:lectures:09_rl_live_withnotes.pdf |}}| | 26.04.2021 online | 10 | **Mid-term exam** from topics covered up to now. Inspiration: quizzes. | | 3.05.2021 online | 11 | Basic concepts of probability (see also: [[https://youtu.be/cFtXkaLog5A?t=496|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|12 - Probability, AI@Berkeley]]) . Bayesian classification and decisions. {{ :courses:be5b33kui:lectures:10_bayes.pdf |}} {{ :courses:be5b33kui:lectures:10_bayes_live_withnotes.pdf |}}| | 10.05.2021 online | 12 | Naive Bayesian classification, Laplace smoothing, Precision, Recall and ROC curve. **Watch** [[https://youtu.be/_pe60buCnxE|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|21 - Machine Learning: Naive Bayes, AI@Berkeley]] **prior to lecture.** (additional online materials: [[https://www.coursera.org/lecture/python-machine-learning/precision-recall-and-roc-curves-8v6DL| ROC curve]], [[https://youtu.be/W5meQnGACGo |video by Andrew Ng]]) {{ :courses:be5b33kui:lectures:11_recog_a.pdf |}} {{ :courses:be5b33kui:lectures:11_recog_a_live_withnotes.pdf |}}| | 17.05.2021 online | 13 | Linear classifiers, perceptron. **Watch** [[https://youtu.be/HEFfs1KCph4?t=43|online video]] from [[http://ai.berkeley.edu/lecture_videos.html|22 - Machine Learning: Perceptrons, AI@Berkeley]] **prior to lecture.** For Nearest neighbor (k-nn) classification, watch [[https://www.youtube.com/watch?v=H9DUTH9lCfg|23 - Machine Learning: Kernels and Clustering]] (only up to min. 16). {{ :courses:be5b33kui:lectures:11_recog_b.pdf |}} {{ :courses:be5b33kui:lectures:11_recog_b_live_withnotes.pdf |}}|