Cybernetics and Artificial Intelligence

Korekvizita:

Předmět nesmí být zapsán současně s:

Cybernetics and Artificial Intelligence (AE3B33KUI)
Kybernetika a umělá inteligence (A3B33KUI)
Kybernetika a umělá inteligence (B3B33KUI)

Předmět je náhradou za:

Cybernetics and Artificial Intelligence (AE3B33KUI)
Kybernetika a umělá inteligence (A3B33KUI)
Kybernetika a umělá inteligence (B3B33KUI)

Garant předmětu:

Tomáš Svoboda

Přednášející:

Petr Pošík, Tomáš Svoboda

Cvičící:

Filipe Gama, Jana Kostlivá, Petr Pošík, Tomáš Svoboda

Předmět zajišťuje:

katedra kybernetiky

Anotace:

The course introduces the students into 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 transition. Students are introduced into reinforcement learning for solving problems when the state transitions are unknown, which also connects the artificial intelligence and cybernetics fields. Bayesian decision task introduces supervised learning. Learning from data is demonstrated on a linear classifier. Students practice the algoritms in computer labs.

Požadavky:

Basic knowledge of linear algebra and programming is assumed. Experience in Python and basics of probability is an advantage.

Osnova přednášek:

What is artificial intelligence and what cybernetics.

Solving problems by search. State space.

Informed search, heuristics.

Games, adversarial search.

Making sequential decisions, Markov decision process.

Reinforcement learning.

Bayesian decision task.

Paramater estimation for probablistic models. Maximum likelihood.

Learning from examples. Linear classifier.

Empirical evaluation of classifiers ROC curves.

Unsupervised learning, clustering.

Osnova cvičení:

Computer lab organization.

Search.

Informed search and heuristics.

Sequential decision problems.

Reinforcement learning.

Pattern Recognition.

Cíle studia:

The course introduces the students into 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 transition. Students are introduced into reinforcement learning for solving problems when the state transitions are unknown, which also connects the artificial intelligence and cybernetics fields. Bayesian decision task introduces supervised learning. Learning from data is demonstrated on a linear classifier. Students practice the algoritms in computer labs.

Studijní materiály:

Stuart J. Russel and Peter Norvig. Artificial Intelligence, a Modern Approach, 3rd edition, 2010

Poznámka:

http://cw.fel.cvut.cz/wiki/courses/be5b33kui/start

Další informace:

https://cw.fel.cvut.cz/wiki/courses/be5b33kui/start

Rozvrh na zimní semestr 2022/2023:

Rozvrh není připraven

Rozvrh na letní semestr 2022/2023:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Po	místnost KN:E-127 Pošík P. Svoboda T. 11:00–12:30 (přednášková par. 1) Karlovo nám. Kotkova cvičebna K4místnost KN:E-132 Gama F. 12:45–14:15 (přednášková par. 1 paralelka 101) Karlovo nám. Laboratoř PC
Út
St
Čt
Pá

Předmět je součástí následujících studijních plánů:

• Electrical Engineering and Computer Science (EECS) (povinně volitelný předmět)
• Electrical Engineering and Computer Science (EECS) (povinně volitelný předmět)