|
Lecturer(s)
|
-
Bělohlávek Radim, prof. RNDr. Ph.D., DSc.
-
Konečný Jan, doc. RNDr. Ph.D.
|
|
Course content
|
Foundations and applications of fuzzy sets, neural networks, and genetic algorithms. 1. Introduction to fuzzy sets: fuzzy sets and operations with fuzzy sets, fuzzy relations and operations with fuzzy relations, basic types of fuzzy relations. 2. Selected applications of fuzzy sets: rule-based systems, fuzzy controllers. 3. Basic concepts f neural networks, neuron, neural network, training and testing set. Simple perceptron and its adaptation. 4. Multilayer neural networks: architecture, universal approximation property, adapration using backpropagation. 5. Hopfield and associative neural networks: architecture, stability, adaptation. 6. Genetic algorithms: basic principles and notions, Holland´s schema theorem. 7. Hopfield and associative networks. 8. Genetic algorithms. 9. Fuzzy-neural networks.
|
|
Learning activities and teaching methods
|
|
Lecture
|
|
Learning outcomes
|
The students become familiar with basic concepts of soft computing.
2. Comprehension Describe and understand comprehensively principles and methods of soft computing.
|
|
Prerequisites
|
unspecified
|
|
Assessment methods and criteria
|
Oral exam, Written exam
Active participation in class. Completion of assigned homeworks. Passing the oral (or written) exam.
|
|
Recommended literature
|
-
Goldberg D. E. (1989). Genetic Algorithms in Search, Optimization & Machine Learning. Addison-Wesley, New York.
-
Klir G. J., Yuan B. (1995). Fuzzy Sets and Fuzzy Logic: Theory and Applications. Prentice-Hall.
-
Rojas R. (1996). Neural Networks: A Systematic Introduction. Springer.
|