Graduate study programme

Back   Schedule   Hrvatski

Soft Computing DRb2-03-18

ECTS 5 | P 30 | A 0 | L 30 | K 0 | ISVU 149752 | Academic year: 2019./2020.

Course groups

Prikaži sve grupe na predmetu

Course lecturers

NYARKO EMMANUEL-KARLO, Lecturer
FILKO DAMIR, Associate

Goals

This course provides the necessary mathematical background for understanding and implementing neural networks, genetic algorithms and fuzzy systems. The course introduces case studies to students where neural networks, genetic algorithms, and fuzzy logic are implemented in solving problems in the area of optimisation, pattern recognition, automatic control, and expert systems.

Conditions for enrollment

Requirements met for enrolling in the study programme

Course description

Comparison of conventional and soft computing methods. Neural networks. Basic concepts, types of networks, learning methods. Applications in signal processing and pattern recognition. Genetic algorithms. Basics of evolution. Concept of individuals and population, definition of genes. Recombination and mutation operators. Fitness functions. Applications in optimisation and pattern classification. Fuzzy logic. Comparison with classical logic, fuzzy sets. Membership functions, fuzzy operators, rules, defuzzification. Application in automatic control and building expert systems. Example of integration of the described methods: adjusting a fuzzy controller using neural networks and genetic algorithms.

Student requirements

Defined by the Student evaluation criteria of the Faculty of Electrical Engineering, Computer Science and Information Technology Osijek and paragraph 1.9

Monitoring of students

Defined by the Student evaluation criteria of the Faculty of Electrical Engineering, Computer Science and Information Technology Osijek and paragraph 1.9

Obligatory literature

1. 1 Tettamanzi, A. G. B; Tomassini, M. Soft Computing: Integrating Evolutionary, Neural, and Fuzzy Systems Springer-Verlag Berlin Heidelberg, 2001.


Pretraži literaturu na:

Recommended additional literature

1. 1 B. Krose, P. van der Smagt An introduction to neural networks University of Amsterdam, 1996.

2. 2 J.-S. R. Jang, C.-T. Sun, E.Mizutani Neuro-Fuzzy and Soft Computing Prentice Hall, 1997.

Course assessment

Conducting university questionnaires on teachers (student-teacher relationship, transparency of assessment criteria, motivation for teaching, teaching clarity, etc.). Conducting Faculty surveys on courses (upon passing the exam, student self-assessment of the adopted learning outcomes and student workload in relation to the number of ECTS credits allocated to activities and courses as a whole).

Overview of course assesment

Learning outcomes
Upon successful completion of the course, students will be able to:

1. compare soft and classical computing

2. describe the basic working principle of a genetic algorithm

3. list several properties of neural networks and their applications

4. compare fuzzy logic with classical logic and list examples where fuzzy logic can be applied

5. adapt a genetic algorithm to solve optimisation problem

6. design neural networks to solve pattern recognition problems



Aktivnosti studenta: Vidi tablicu aktivnosti