Lecturer(s)
|
-
Skrbek Miroslav, Ing. Ph.D.
|
Course content
|
The course is focused on advanced neural network algorithms. The theory is combined with practical experiments in the Python programming language. 1. Basic models of neural networks 2. Supervised learning, gradient methods 3. Unsupervised learning, SOM, LVQ, Neural gas 4. Experiments with neural networks in Python I 5. Experiments with neural networks in Python II 5. Recurrent neural networks, LSTM 6. Experiments with recurrent networks in Python I 7. Experiments with recurrent networks in Python II 8. Convolution neural networks 9. Deep learning 10. Neural Turing machines 11. Deep learning frameworks: Tensorflow, Keras 12. Pre-learned deep neural networks, applications and modification 13. Experiments with deep learning in Python I 14. Experiments with deep learning in Python II
|
Learning activities and teaching methods
|
Monologic (reading, lecture, briefing), Laboratory
- Semestral paper
- 20 hours per semester
- Class attendance
- 26 hours per semester
- Preparation for classes
- 13 hours per semester
- Preparation for exam
- 20 hours per semester
|
Learning outcomes
|
The aim of the course is to provide deeper knowledge of computational intelligence. The course focuses on the implementation of selected algorithms and experiments with them.
In this course, students obrain deeper knowledge in computational intelligence, especially neural networks.
|
Prerequisites
|
Programming knowledge, programming in Python is advantage
|
Assessment methods and criteria
|
Written examination, Seminar work
Each student may take 100 points (30 points examination, 70 points tutorial). For passing examination, the total number of points (examination and tutorial) must be greater or equal to 50 and the examination test must be evaluated to one half points or more. If any of these conditions is not satisfied, the student fails.
|
Recommended literature
|
-
Andries P. Engelbrecht: Computational intelligence: An Introduction. Wiley; 2 edition, 2007. ISBN: 978-0470035610.
-
Simon Haykin: Neural Networks and Learning Machines. Third Edition. Prentice Hill. 2009. ISBN 978-0-13-147139-9..
-
ŠÍMA, J. - NERUDA, R.: Teoretické otázky neuronových sítí. Matfyzpress, Praha, 1996..
|