Contacts: Tomas Svoboda, Matej Hoffmann, Petr Svarny

The course introduces the students to the field of artificial intelligence and gives the necessary basis for designing machine control algorithms. It advances the knowledge of state space search algorithms by including uncertainty in a state transition. Students are introduced into reinforcement learning for solving problems when the state transitions are unknown, which also connects the artificial intelligence and cybernetics fields. Bayesian decision task introduces supervised learning. Learning from data is demonstrated on a linear classifier. Students practice the algorithms in computer labs.

The course expects some basics of probability and linear algebra to be known to students. We expect that students are able to write decent computer programs in a higher level language (Java, Python), and have basic knowledge about data structures. Python and Matlab will be used in computer labs.

Will take place during the lecture on **2018-04-30**. It will contain exercises from the topic covered so far, i.e. “Search and planning”. It will be a 30min written test.

points: 50 for homework and 15 for the mid-term exam make together 65 points from the term work. The final exam is worth 35 points. At least 20 points (out of 50) for the homework are needed for the assessment and before going to the final exam. There will be some bonus points for discussions. Minimum for a non-F grade is 15 points from the final exam.

A | B | C | D | E | F |
---|---|---|---|---|---|

100-91 | 90-81 | 80-71 | 70-61 | 60-51 | 50-0 |

**F** means fail.