Subject description - BE4M36SMU

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
BE4M36SMU Symbolic Machine Learning Extent of teaching:2P+2C
Guarantors:Železný F. Roles:PO,PV Language of
teaching:
EN
Teachers:Kuželka O., Železný F. Completion:Z,ZK
Responsible Department:13136 Credits:6 Semester:L

Anotation:

The course will explain methods through which an intelligent agent can learn, that is, improve its behavior from observed data and background knowledge. The learning scenarios will include on-line learning and learning from i.i.d. data (along with the PAC theory of learnability), as well as the active and reinforcement learning scenarios. Agent's knowledge will be represented through the language of logic and through graphical models. The course is given in English to all students.

Course outlines:

1. Agent-environment model, interaction principles
2. Concept learning, on-line learnability, version space
3. Learning from i.i.d. data, PAC-learnability, VC-dimension
4. Learnability of propositional-logic concepts
5. Learning a graphical probabilistic model
6. Learning a graphical probabilistic model (2)
7. PAC-learning predicate-logic CNF
8. Learning predicate-logic clauses
9. Learning a relational graphical probabilistic model
10. Learning a relational graphical probabilistic model (2)
11. Active learning
12. Reinforcemenent learning
13. Reinforcemenent Learning (2)
14. Solomonoff induction and universal AI

Exercises outline:

Literature:

Course textbook available at https://cw.fel.cvut.cz/wiki/courses/smu/start Stuart Russell and Peter Norvig: Artificial Intelligence: A Modern Approach, Prentice Hall 2010 Luc De Raedt: Logical and Relational Learning, Springer 2008 Marcus Hutter: Universal artificial intelligence, Springer 2005

Requirements:

Subject is included into these academic programs:

Program Branch Role Recommended semester
MEOI7_2018 Artificial Intelligence PO 2
MEOI9_2016 Data Science PO 2
MEOI7_2016 Artificial Intelligence PO 2
MEOI8_2016 Bioinformatics PO 2
MEBIO_2018 Common courses PV 2
MEOI9_2018 Data Science PO 2
MEOI8_2018 Bioinformatics PO 2


Page updated 18.9.2019 17:53:12, semester: Z,L/2020-1, L/2018-9, Z,L/2019-20, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)