Subject description - BE5B33KUI

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
BE5B33KUI Cybernetics and Artificial Intelligence
Roles:PV Extent of teaching:2P+2C
Department:13133 Language of teaching:EN
Guarantors:Svoboda T. Completion:Z,ZK
Lecturers:Pošík P., Svoboda T. Credits:6
Tutors:Too many persons Semester:L

Web page:

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

Anotation:

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.

Study targets:

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.

Course outlines:

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.

Exercises outline:

Computer lab organization. Search. Informed search and heuristics. Sequential decision problems. Reinforcement learning. Pattern Recognition.

Literature:

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

Requirements:

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

Note:

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

Keywords:

Cybernetics, artificial intelligence

Subject is included into these academic programs:

Program Branch Role Recommended semester
BPEECS_2018 Common courses PV 4
BEECS Common courses PV 4


Page updated 29.3.2024 09:50:44, semester: Z/2024-5, Z,L/2023-4, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)