13S053NM - Neural Networks

Course specification
Course title		Neural Networks
Acronym		13S053NM
Study programme		Software Engineering
Module
Type of study		bachelor academic studies
Lecturer (for classes)		professor PhD Goran Kvaščev professor PhD Aleksandar Rakić
Lecturer/Associate (for practice)		asst. MA Marija Novičić, electrical and computer engineer professor PhD Sanja Vujnović asst. Aleksa Stojić, electrical and computer engineer professor PhD Aleksandar Rakić
Lecturer/Associate (for OTC)		professor PhD Aleksandar Rakić asst. MA Marija Novičić, electrical and computer engineer
ESPB		6.0	Status	elective
Condition		none
The goal		Introduce students to the basic concepts of neural networks and fuzzy logic systems. Presentation of various architectures, design methods, tuning and implementation.
The outcome		Students will be able to independently analyze and synthesize different types of neural networks and fuzzy logic systems for various engineering applications, including signal processing, control design, classification, regression, knowledge extraction. They will also learn to develop and implement such systems using modern programming environments (Matlab and Python).
Contents
Contents of lectures		Development of neural networks, architecture and problems. Function approximation, data clustering, time series and modeling of dynamic systems. Backpropagation, generalization, overfitting and initialization. Classification and clustering. Dynamic networks. Deep networks. Convolutional networks. LSTM. Concepts of fuzzy logic. Mamdani and Sugeno machine model. Design and tuning of fuzzy systems.
Contents of exercises		Computer exercises for the design and analysis of neural networks and fuzzy logic. Solving practical problems from various fields of engineering using modern programming environments (Matlab and Python).
Literature
Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems, Chin-Teng Lin, C. S. George Lee, Prentice Hall, 1996 (Original title) Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville, The MIT Press, 2017 (Original title) Grokking Deep Learning, Andrew Trask, Manning, 2019 (Original title) Deep Learning with Python, 2nd Edition, Francois Chollet, Manning, 2021 (Original title) T. J. Ross, Fuzzy Logic with Engineering Applications, 3rd ed. Hoboken, NJ, USA: Wiley, 2010. (Original title)
Number of hours per week during the semester/trimester/year
Lectures	Exercises	OTC	Study and Research	Other classes
2	2	1
Methods of teaching		Lectures, exercises on computers
Knowledge score (maximum points 100)
Pre obligations		Points	Final exam	Points
Activites during lectures		0	Test paper	30
Practical lessons		0	Oral examination	0
Projects		30
Colloquia		40
Seminars		0