Neural Networks and Computational Intelligence
- Pavel Surynek (guarantor)
- Department of Applied Mathematics
Theoretical foundations of neural networks with a focus on advanced paradigms and the use of neural networks as a model for data analysis and data mining. Networks with dynamically generated topology during learning developed on the principles of inductive modeling. Evolutionary techniques and nature-inspired optimization. Principles of machine learning, deep neural networks and deep learning.
- Syllabus of lectures:
1. Theoretical foundations of artificial neural networks.
2. Neural networks for classification and approximation.
3. Methods of learning (with and without a supervisor), advanced gradient methods and evolutionary learning algorithms.
4. Development of neural network topology by evolutionary techniques, genetic programming.
5. Networks with complex scales.
6. Self-organization for analyzing and extracting knowledge from data.
8. Inductive modeling methods, automated design of the model by computational intelligence methods.
9. Nature-inspired optimization techniques.
10. Machine learning using neural networks
11. Deep neural networks and deep learning
- Syllabus of tutorials:
- Study Objective:
To familiarize students with theoretical backgrounds and advanced methods in the field of neural networks, especially in the field of learning, development of topology and modeling of data analysis and extraction.
- Study materials:
 Simon Haykin: Neural Networks and Learning Machines. Third Edition. Prentice Hall, 2009, ISBN 978-0-13-147139-9.
 Sundararajan, N., Saratchandran, P.: Parallel Architectures for Artificial Neural Networks, IEEE Computer Society Press, 1998, ISBN 0-8186-8399-6.
 Šíma, J., Neruda, R.: Theoretical Issues of Neural Networks
MATFYZPRESS, Prague, 1996, ISBN 80-85863-18-9.
 Aggarwal, Charu C.: Neural Networks and Deep Learning, Springer 2018, ISBN 978-3-319-94463-0.
- Further information:
- No time-table has been prepared for this course
- The course is a part of the following study plans: