Artificial Intelligence 2 - NAIL070
Title: Umělá inteligence 2
Guaranteed by: Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
Faculty: Faculty of Mathematics and Physics
Actual: from 2020
Semester: summer
E-Credits: 3
Hours per week, examination: summer s.:2/0, Ex [HT]
Capacity: unlimited
Min. number of students: unlimited
4EU+: no
Virtual mobility / capacity: no
State of the course: taught
Language: Czech, English
Teaching methods: full-time
Teaching methods: full-time
Additional information: http://ktiml.mff.cuni.cz/~bartak/ui2/
Guarantor: prof. RNDr. Roman Barták, Ph.D.
Class: Informatika Mgr. - Teoretická informatika
Classification: Informatics > Theoretical Computer Science
Opinion survey results   Examination dates   SS schedule   Noticeboard   
Annotation -
The course covers uncertainty in artificial intelligence, decision making, and basic methods of machine learning.
Last update: Barták Roman, prof. RNDr., Ph.D. (05.06.2017)
Aim of the course -

To learn the following techniques of artificial intelligence: uncertainty reasoning, decision making, machine learning.

Last update: Barták Roman, prof. RNDr., Ph.D. (06.10.2017)
Course completion requirements -

The course is concluded by an oral exam, that could be, in exceptional cases, in an on-line form.

Last update: Barták Roman, prof. RNDr., Ph.D. (28.04.2020)
Literature -

S. Russell, P. Norvig: Artificial Intelligence; A Modern Approach, 2003

V. Mařík, O. Štepánková, J. Lažanský a kol.: Umělá Inteligence, 1-6. Academia, Praha

Last update: Barták Roman, prof. RNDr., Ph.D. (06.10.2017)
Teaching methods -

lectures

Last update: Barták Roman, prof. RNDr., Ph.D. (06.10.2017)
Requirements to the exam -

The exam consists of a written preparation and an oral part. The requirements are given by the course syllabus.

Last update: Barták Roman, prof. RNDr., Ph.D. (06.10.2017)
Syllabus -

Uncertainty reasoning: probabilistic methods, Bayesian networks, Markov models.

Decision making: utility theory, Markov Decision Processes, decisions with multiple agents, (inverse) game theory.

Machine learning: supervised learning, decision trees, regression, SVM, boosting; version space search; learning probabilistic models, the EM algorithm; reinforcement learning.

Last update: Barták Roman, prof. RNDr., Ph.D. (05.06.2017)