Neural Networks and their Applications 1

Garant předmětu:

František Hakl

Lecturer:

František Hakl, Martin Holeňa

Tutor:

Supervisor:

Department of Mathematics

Synopsis:

Keywords:

Neural networks, data separation, functional approximation, supervised learning

Requirements:

Syllabus of lectures:

1.Basic concepts of artificial neural networks.

2.Most common kinds artificial neural networks.

3.Basic numerical methods for neural networks learning.

4.Network design and architecture optimization techniques.

5.Overview of basic types of problems solved by neural networks.

6.Working with artificial neural networks in the Matlab and ROOT.

Syllabus of tutorials:

Study Objective:

Acquired knowledge:

Basic concepts, features and models of neural networks.

Acquired skills:

Orientation in the art, the ability to use models of artificial neural networks for solving practical problems in the field of approximation of functions, separation of sets and time series prediction.

Study materials:

Compulsory literature:

[1] R. Rojas. Neural Networks ? A Systematic Introduction. Springer. 1991

Optional literature:

[2] B.D. Ripley. Pattern Recognition and Neural Networks. Cambridge University Press. 1996

Note:

Time-table for winter semester 2023/2024:

Time-table is not available yet

Time-table for summer semester 2023/2024:

Time-table is not available yet

The course is a part of the following study plans:

• Matematické inženýrství (elective course)
• Aplikovaná algebra a analýza (elective course)
• Aplikované matematicko-stochastické metody (elective course)
• Jaderná a částicová fyzika (elective course)
• Matematická informatika (compulsory course in the program)
• Fyzikální elektronika - Počítačová fyzika (elective course)