Neural Networks

Course Description

The course provides knowledge in theory and applications of artificial neural networks and genetic algorithms. Biological neural networks. Artificial neural networks. Definition. Neuron models. Activation function. Network topologies. Perceptron. Learning laws. Associative networks. Linear associator. Recursive associative networks. Hopfield network. Energy function. Multi-layer networks. Radial-basis function networks. Support vector machine. Delta rule for error back-propagation. Kohonen self-organizing network. K-means clustering algorithm. Boltzmann machine. Simulated annealing. Genetic algorithms. Software for simulation of neural networks. Applications in pattern recognition and signal and image analysis.

General Competencies

Student acquires basic knowledge in concepts and methods for artificial neural networks with applications in pattern recognition and analysis of various types of information such as signals and images, in various application areas. Students gain knowledge on neuron models, learning algorithms, associative networks, Rosenblatt perceptron, multi-layer perceptron, radial-basis function networks, support vector machines, recursive networks, self-organising networks, and genetic algorithms. Students are able to use computer software for neural network simulation to implement neural networks.

Learning Outcomes

  1. define and describe concepts of artificial neural networks
  2. list examples of neural network applications
  3. classify methods for artificial neural networks
  4. breakdown a practical problem of neural network learning and exploitation
  5. combine acquired knowledge and propose a solution to the given problem
  6. evaluate a practical solution obtained using neural networks

Forms of Teaching


Lectures are delivered according to the published plan and on the basis of the materials that are made available to the students.


Student exams are in the form of a mid-term exam and a final exam that are graded together with other student activities. Students who do not pass through continuing evaluation can take exam at a final examination term.

Laboratory Work

Laboratory excercises are completed according to the published plan and based on the instructions available to students. Laboratory involves software implementation of various neural networks.


Oral consultations are available on student request.

Other Forms of Group and Self Study

Student team project.

Grading Method

Continuous Assessment Exam
Type Threshold Percent of Grade Threshold Percent of Grade
Laboratory Exercises 50 % 20 % 50 % 0 %
Seminar/Project 50 % 20 % 50 % 0 %
Mid Term Exam: Written 50 % 30 % 0 %
Final Exam: Written 50 % 30 %
Exam: Written 60 % 50 %
Exam: Oral 50 %

Week by Week Schedule

  1. Introductory course remarks. Introduction to neural networks - part one.
  2. Introduction to neural networks - part two.
  3. Learning process. Associative memory.
  4. Rosenblatt perceptron. LMS algoritam.
  5. Multilayer perceptron.
  6. Radial-basis function networks.
  7. Support vector machine.
  8. Midterm exam.
  9. Recursive networks. Hopfield network.
  10. Self-organizing networks.
  11. Genetic algorithms and evolutionary strategies.
  12. Neurocomputers.
  13. Practical applications of neural networks.
  14. Presentations of student team projects.
  15. Final exam.

Study Programmes

University graduate
Computer Engineering (profile)
Recommended elective courses (3. semester)
Computer Science (profile)
Recommended elective courses (3. semester)
Electronic and Computer Engineering (profile)
Recommended elective courses (3. semester)
Information Processing (profile)
Specialization Course (1. semester) (3. semester)
Software Engineering and Information Systems (profile)
Recommended elective courses (3. semester)
Telecommunication and Informatics (profile)
Recommended elective courses (3. semester)


S. Lončarić (2011.), Predavanja iz neuronskih mreža, FER-ZESOI
S. Haykin (1998.), Neural Networks, 2nd Ed., Prentice Hall
J. A. Anderson (1995.), An Introduction to Neural Networks, MIT Press

Associate Lecturers

Laboratory exercises


ID 127251
  Winter semester
L2 English Level
L1 e-Learning
30 Lectures
0 Exercises
15 Laboratory exercises
0 Project laboratory

Grading System

89 Excellent
79 Very Good
70 Good
61 Acceptable