Subject description - B4M36SMU

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
B4M36SMU Symbolic Machine Learning
Roles:PV, PO Extent of teaching:2P+2C
Department:13136 Language of teaching:CS
Guarantors:Kuželka O. Completion:Z,ZK
Lecturers:Kuželka O., Šír G., Železný F. Credits:6
Tutors:Too many persons Semester:L

Web page:

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

Anotation:

This course consists of four parts. The first part of the course will explain methods through which an intelligent agent can learn by interacting with its environment, also known as reinforcement learning. This will include deep reinforcement learning. The second part focuses on Bayesian networks, specifically methods for inference. The third part will cover fundamental topics from natural language learning, starting from the basics and ending with state-of-the-art architectures such as transformer. Finally, the last part will provide an introduction to several topics from the computational learning theory, including the online and batch learning settings.

Course outlines:

1. Reinforcement Learning - Markov decision processes
2. Reinforcement Learning - Model-free policy evaluation
3. Reinforcement Learning - Model-free control
4. Reinforcement Learning - Deep reinforcement learning
5. Bayesian Networks - Intro
6. Bayesian Networks - Variable elimination, importance sampling
7. Natural Language Processing 1
8. Natural Language Processing 2
9. Natural Language Processing 3
10. Natural Language Processing 4
11. Computational Leaning Theory 1
12. Computation Learning Theory 2
13. Computational Learning Theory 3.
14. Course Wrap Up

Exercises outline:

1. Reinforcement Learning - Markov decision processes
2. Reinforcement Learning - Model-free policy evaluation
3. Reinforcement Learning - Model-free control
4. Reinforcement Learning - Deep reinforcement learning
5. Bayesian Networks - Intro
6. Bayesian Networks - Variable elimination, importance sampling
7. Natural Language Processing 1
8. Natural Language Processing 2
9. Natural Language Processing 3
10. Natural Language Processing 4
11. Computational Leaning Theory 1
12. Computation Learning Theory 2
13. Computational Learning Theory 3.
14. Course Wrap Up

Literature:

R. S. Sutton, A. G. Barto: Reinforcement learning: An introduction. MIT press, 2018.
D. Jurafsky & J. H. Martin: Speech and Language Processing - 3rd edition draft
M. J. Kearns, U. Vazirani: An Introduction to Computational Learning Theory, MIT Press 1994

Requirements:

Students can get a maximum of 100 points which is the sum of the projects score and the exam score. A minimum of 25 (out of 50) exam points is required to pass the exam. A minimum of 25 (out of 50) projects points is required to obtain an assessment.

Keywords:

Reinforcement learning, Bayesian networks, natural language processing, computational learning theory

Subject is included into these academic programs:

Program Branch Role Recommended semester
MPBIO1_2018 Bioinformatics PV 2
MPOI7_2018 Artificial Intelligence PO 2
MPBIO2_2018 Medical Instrumentation PV 2
MPBIO3_2018 Image processing PV 2
MPOI9_2018 Data Science PO 2
MPOI8_2018 Bioinformatics PO 2
MPBIO4_2018 Signal processing PV 2


Page updated 4.12.2024 17:51:26, semester: Z,L/2024-5, Z/2025-6, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)