Logo ČVUT
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2017/2018

Cybernetics and Artificial Intelligence

Login to KOS for course enrollment Display time-table
Code Completion Credits Range Language
B3B33KUI Z,ZK 6 2p+2c Czech
The course cannot be taken simultaneously with:
Cybernetics and Artificial Intelligence (AE3B33KUI)
Cybernetics and Artificial Intelligence (A3B33KUI)
Cybernetics and Artificial Intelligence (BE5B33KUI)
The course is a substitute for:
Cybernetics and Artificial Intelligence (A3B33KUI)
Lecturer:
Tutor:
Supervisor:
Department of Cybernetics
Synopsis:

The course introduces the students into 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 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 algoritms in computer labs.

Requirements:

Basic knowledge of probability and linear algebra is assumed. We expected student is able to write decent computer programs in a higher level language (Java, Python), and have basic knowledge about data structures. Python will be used in computer labs.

Syllabus of lectures:

What is artificial intelligence and what cybernetics.

Solving problems by search. State space.

Informed search, heuristics.

Games, adversarial search.

Making sequential decisions, Markov decision process.

Reinforcement learning.

Bayesian decision task.

Paramater estimation for probablistic models. Maximum likelihood.

Learning from examples. Linear classifier.

Empirical evaluation of classifiers ROC curves.

Unsupervised learning, clustering.

Syllabus of tutorials:

Computer lab organization.

Search.

Informed search and heuristics.

Sequential decision problems.

Reinforcement learning.

Pattern Recognition.

Study Objective:

The course introduces the students into 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 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 algoritms in computer labs.

Study materials:

Stuart J. Russel and Peter Norvig. Artificial Intelligence, a Modern Approach, 3rd edition, 2010

Note:
Further information:
http://cw.fel.cvut.cz/wiki/courses/b3b33kui/start
Time-table for winter semester 2017/2018:
Time-table is not available yet
Time-table for summer semester 2017/2018:
Time-table is not available yet
The course is a part of the following study plans:
Data valid to 2017-11-23
For updated information see http://bilakniha.cvut.cz/en/predmet4674006.html