Soft Computing

Data is displayed for academic year: 2023./2024.

Lecturers

Assoc. Prof.
Marko Čupić

Laboratory exercises

Mihael Jakšić
univ. mag. ing, comp.

Course Description

Soft computing is a group of methods that differ from classical computational methods in very fundamental ideas. They are based on approximate reasoning, self learning, parallelism and non-determinism. Inspiration for these methods comes from biology e.g. biological neuron, process of evolution, human like approximate reasoning etc. These methods can solve problems that cannot be solved by applying classical mathematical and computational methods and they are used in scientific research and in myriad applications and everyday products.

Study Programmes

University graduate
[FER3-HR] Audio Technologies and Electroacoustics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Communication and Space Technologies - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computational Modelling in Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computer Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computer Science - profile
Elective Courses (1. semester) (3. semester)
Elective Courses of the Profile (1. semester) (3. semester)
[FER3-HR] Control Systems and Robotics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Data Science - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electrical Power Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electric Machines, Drives and Automation - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electronic and Computer Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electronics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Information and Communication Engineering - profile
Elective Courses (1. semester) (3. semester)
Elective Courses of the Profile (1. semester)
Elective Coursesof the Profile (3. semester)
[FER3-HR] Network Science - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Software Engineering and Information Systems - profile
Elective Course of the profile (3. semester)
Elective Course of the Profile (1. semester)
Elective Courses (1. semester) (3. semester)
[FER2-HR] Computer Engineering - profile
Recommended elective courses (3. semester)
[FER2-HR] Computer Science - profile
Specialization Course (1. semester) (3. semester)
[FER2-HR] Software Engineering and Information Systems - profile
Recommended elective courses (3. semester)
[FER2-HR] Telecommunication and Informatics - profile
Recommended elective courses (3. semester)

Learning Outcomes

  1. describe and define basic areas of soft computing
  2. apply fuzzy logic models on control problems
  3. apply artificial neural networks for prediction and classification tasks
  4. solve optimization problems using evolutionary computation
  5. combine different soft computing techniques into complete system
  6. select the appropriate soft computing method for solving various problems

Forms of Teaching

Lectures

Laboratory

Week by Week Schedule

  1. Fuzzy sets and fuzzy logic
  2. Fuzzy sets and fuzzy logic
  3. Fuzzy sets and fuzzy logic
  4. Fuzzy sets and fuzzy logic
  5. Fuzzy logic inference (fuzzy propositions, fuzzy relations, and fuzzy implications), Fuzzy inference engines; fuzzyfication and defuzzyfication
  6. Fuzzy logic inference (fuzzy propositions, fuzzy relations, and fuzzy implications), Fuzzy inference engines; fuzzyfication and defuzzyfication
  7. Perceptron (learning paradigms,Hebbian learning, competitive learning, Boltzmann learning), Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time)
  8. Midterm exam
  9. Self-organizing networks (Hebbian non-supervised learning, Oja's learning rule, PCA using self-organizing network, Sanger's learning rule, Competitive non-supervised learning, winner-takes-all network, Kohonen's self-organizing maps)
  10. Fuzzy inference engines; fuzzyfication and defuzzyfication, Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time)
  11. Evolutionary algorithms for SOOP
  12. Evolutionary algorithms for SOOP
  13. Evolutionary algorithms for SOOP, Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time)
  14. Fuzzy inference engines; fuzzyfication and defuzzyfication, Fuzzy clustering, Evolutionary algorithms for SOOP
  15. Final exam

Literature

(.), Marko Čupić, Bojana Dalbelo Bašić, Marin Golub. Neizrazito, evolucijsko i neuroračunarstvo, 2012. (online),
(.), Z.Michalewicz: Genetic Algorithms + Data Structures = Evolution Programs, Springer Verlag, Berlin, 3rd ed., 1996.,
(.), S.Haykin: Neural Networks, Comprehensive Foundation, Prentice Hall, 2nd ed., 1999.,
(.), J. Yen and R. Langari: Fuzzy Logic, Prentice Hall, 1999.,
(.), H.J.Zimmermann: Fuzzy Set Theory and Its Applications, Kluwer Academic Publishers, 4th ed., 2001.,

For students

General

ID 222649
  Winter semester
5 ECTS
L0 English Level
L1 e-Learning
45 Lectures
0 Seminar
0 Exercises
15 Laboratory exercises
0 Project laboratory
0 Physical education excercises

Grading System

Excellent
Very Good
Good
Sufficient