Subject description - BE3M33UI

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
BE3M33UI Artificial Intelligence Extent of teaching:2p+2c
Guarantors:Pošík P. Roles:PO,PV Language of
teaching:
EN
Teachers:Mařík R., Pošík P. Completion:Z,ZK
Responsible Department:13133 Credits:6 Semester:L

Anotation:

The course deepens and enriches knowledge of AI gained in the bachelor course Cybernetics and Artificial Intelligence. Students will get an overview of other methods used in AI, and will get a hands-on experience with some of them. They will master other required abilities to build intelligent agents. By applying new models, they will reiterate the basic principles of machine learning, techniques to evaluate models, and methods for overfitting prevention. They will learn about planning and scheduling tasks, and about methods used to solve them. Student will also get ackquainted with the basics of probabilistic graphical models, Bayesian networks and Markov models, and will learn their applications. Part of the course will introduce students to the area of again populat neural networks, with an emphasis to new methods for deep learning.

Course outlines:

1. The relation of artificial intelligence, pattern recognition, learning and robotics. Decision tasks, Empirical learning.
2. Linear methods for classification and regression.
3. Non-linear models. Feature space straightening. Overfitting.
4. Nearest neighbors. Kernel functions, SVM. Decision trees.
5. Bagging. Adaboost. Random forests.
6. Graphical models. Bayesian networks.
7. Markov statistical models. Markov chains.
8. Expectation-Maximization algorithm.
9. Planning. Planning problem representations. Planning methods.
10. Scheduling. Local search.
11. Neural networks. Basic models and methods, error backpropagation.
12. Special neural networks. Deep learning.
13. Constraint satisfaction problems.
14. Evolutionary algorithms..

Exercises outline:

Students will solve practical tasks. They will get experience with chosen packages for machine learning, graphical models, neural networks, etc. and will implement parts of algorithms themselves.

Literature:

S. Russel, P. Norvig: Artificial Intelligence - A Modern Approach, 3rd ed., 2010
C. M. Bishop: Pattern Recognition and Machine Learning, 2006

Requirements:

Topics covered by course B3B33KUI.

Webpage:

http://cw.fel.cvut.cz/wiki/courses/be3m33ui/start

Subject is included into these academic programs:

Program Branch Role Recommended semester
MEKYR5_2016 Cybernetics and Robotics PV 2
MEKYR2_2016 Sensors and Instrumentation PV 3
MEKYR1_2016 Robotics PO 2
MEKYR4_2016 Air and Space Systems PV 3
MEKYR3_2016 Systems and Control PV 3


Page updated 21.9.2018 17:49:42, semester: Z,L/2020-1, L/2017-8, L/2019-20, Z,L/2018-9, Z/2019-20, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)