Symbolic Machine Learning

Semestr: Summer

Range: 2P+2C


Credits: 6

Programme type:

Study form: Fulltime

Course language: Czech

Time table at FEE


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. Symbolic knowledge representations (mainly through logic and graphs) will be used where possible. The course is given in English to all students.


Course syllabus:

1. General framework, passive reinforcement learning
2. TD agent, active R/L, Q-learning
3. SARSA agent, state representation, policy search, AIξ agent
4. Universal sequence prediction, AIXI agent; Non-sequential concept learning.
5. Online learning, mistake-bound model
6. Batch learning, PAC-learning model
7. Learning first-order logic conjunctions
8. Learning first-order logic clauses
9. Learning with queries
10. Bayesian networks
11. Bayesian networks
12. Probabilistic (logic) programming
13. Probabilistic (logic) programming

Seminar syllabus:

1 Introduction, Python environment, entrance test
2 PEAS agent model, environment properties, input/output types of machine learning models, demos
3 Learning conjunctive and disjunctive concepts
4 Assignment of the first student project
5 Bayesian Networks - semantics
6 Bayesian Networks - inference
7 Assignment of the second student project
8 Inductive Logic Programming - learning from interpretations
9 Inductive Logic Programming - learning from clauses
10 ILP, Q&A
11 Reinforcement learning, demos and introduction
12 Assignment of the fourth project
13 Passive reinforcement learning agents, TD methods
14 Reserve, assessment


Lecture slides available at

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