|
Lecturer(s)
|
-
Skrbek Miroslav, Ing. Ph.D.
-
Bukovský Ivo, doc. Ing. Ph.D.
|
|
Course content
|
1. Introduction to computational intelligence 2. Neural networks, taxonomy, topology 3. Feed-forward networks, supervised learning, Perceptron, RBF 4. Gradient learning methods, Back propagation algorithm 5. Self-organizing neural networks, SOM 6. Recurrent neural networks 7. Convolutional neural networks and deep learning 8. Application of neural networks 9. Reinforcement learning 10. Fuzzy systems: fuzzy set, fuzzy rules, fuzzification, inference, defuzzification. 11. Genetic algorithms, a principle 12. Differential evolution, genetic programming 13. Optimization inspired by nature, PSO (Particle Swarm Optimization) algorithm and ANT (Ant Colony Optimization)
|
|
Learning activities and teaching methods
|
Monologic (reading, lecture, briefing), Project-based learning, Practical training, Case studies
- Preparation for exam
- 25 hours per semester
- Preparation for classes
- 25 hours per semester
- Class attendance
- 28 hours per semester
- Semestral paper
- 22 hours per semester
|
|
Learning outcomes
|
The course aims to acquaint students with the basics of algorithms in neural networks and computational intelligence, with the essential tools for their use (with emphasis on today's commonly used open-source SW tools), and with some typical applications for their use. The course includes neural networks, fuzzy systems, evolutionary algorithms, and nature-inspired optimization algorithms.
Basic work with data on a PC, the ability of mathematical analysis and task solving using programming tools.
|
|
Prerequisites
|
Basics of programming (any programming language, knowledge of working in Python and Jupyter Notebook an advantage), knowledge of mathematics in basic bachelor's degree courses.
|
|
Assessment methods and criteria
|
Oral examination, Test, Development of laboratory protocols, Interim evaluation
Create and defend the semestral project, pass the exam test, get at least 50% of all possible points.
|
|
Recommended literature
|
-
Anupam Prof. Shukla, Ritu Tiwari. Discrete Problems in Nature Inspired Algorithms. CRC Press; 1st edition, December 26, 2017. ISBN 978-1138196063.
-
Guanrong Chen and Trung Tat Pham. Introduction to Fuzzy Sets, Fuzzy Logic, and Fuzzy Control Systems. CRC Press; 1st edition, October 7, 2019. ISBN 978-0367397883.
-
CHARU C. AGGARWAL. Neural Networks and Deep Learning: A Textbook. Springer; 1st ed. 2018. ISBN: 978-3319944623. ISBN 978-3319944623.
-
XIN-SHE YANG. Nature-Inspired Optimization Algorithms, 2nd Edition. Academic Press, September 2020. 978-0128219867.
|