Subject description - BECM36MLM

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
BECM36MLM Machine Learning Methods
Roles:P Extent of teaching:2P+2C
Department:13136 Language of teaching:EN
Guarantors:Železný F. Completion:Z,ZK
Lecturers:Kuželka O., Šír G., Železný F. Credits:6
Tutors:Krutský M., Kuželka O., Peleška J., Šír G. Semester:L

Web page:

https://cw.fel.cvut.cz/b252/courses/becm36mlm/start

Anotation:

Students will get familiar with advanced machine learning methods (MLM) that go beyond common data domains (vision, text) taught in the other courses (e.g., BE4M33MPV, BECM36NLPT). They will learn techniques that work well for tabular and structured data (e.g., relational databases), including rule/tree ensembles, graph neural networks, and other advanced approaches aimed at complex learning problems. Additionally, the course will also teach students methods for model interpretability, the basics of causality, and reinforcement learning.

Course outlines:

1. Learning from Tabular data
2. Learning from Structured data
3. Graph Neural Networks
4. Relational Deep Learning
5. Neural-Symbolic Learning
6. Learning with Large Language Models
7. Interpretability of ML Models
8. Potential outcomes - Rubin-Neyman causal model, uplift modeling
9. Intro to “Pearl’s” causality
10. A/B tests and multi-armed bandit problems, UCB algorithm.
11. Bayesian bandits (Thompson sampling). Contextual bandits.
12. Markov decision processes
13. Tabular RL: Q-Learning and SARSA
14. Deep RL: Deep Q-learning. Policy gradient.

Exercises outline:

1. Learning from Tabular data
2. Learning from Structured data
3. Graph Neural Networks
4. Relational Deep Learning
5. Neural-Symbolic Learning
6. Learning with Large Language Models
7. Interpretability of ML Models
8. Potential outcomes - Rubin-Neyman causal model, uplift modeling
9. Intro to “Pearl’s” causality
10. A/B tests and multi-armed bandit problems, UCB algorithm.
11. Bayesian bandits (Thompson sampling). Contextual bandits.
12. Markov decision processes
13. Tabular RL: Q-Learning and SARSA
14. Deep RL: Deep Q-learning. Policy gradient.

Literature:

Requirements:

This is an advanced ML course that assumes at least some prior knowledge of ML (e.g., B4B33RPZ, BECM33MLF), data representation (e.g., B0B36DBS, B0B01LGR), and deep learning (e.g., BECM33DPL).

Subject is included into these academic programs:

Program Branch Role Recommended semester
MPPRGAI_2025 Common courses P 2

Page updated 19.4.2026 17:51:07, semester: L/2025-6, L/2029-30, Z/2028-9, Z/2025-6, L/2028-9, Z/2026-7, Z,L/2027-8, L/2026-7, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)
Responsible person: prof. Ing. Jiří Jakovenko, Ph.D.