13M054NM - Neural Networks and System for Signal Processing

Course specification
Course title		Neural Networks and System for Signal Processing
Acronym		13M054NM
Study programme		Electrical Engineering and Computing
Module		Applied Mathematics, Audio and Video Technologies, Biomedical and Environmental Engineering, Biomedical and Nuclear Engineering, Computer Engineering and Informatics, Electronics and Digital Systems, Energy Efficiency, Information and communication technologies, Information and Communication Technologies, Microwave Engineering, Nanoelectronics and Photonics, Power Systems - Networks and Systems, Power Systems - Renewable Energy Sources, Power Systems - Substations and Power Equipment, Signals and Systems, Software Engineering
Type of study		master academic studies
Lecturer (for classes)		professor PhD Goran Kvaščev
Lecturer/Associate (for practice)		asst. MA Marija Novičić, electrical and computer engineer asst. MA Aleksa Stojić, electrical and computer engineer
Lecturer/Associate (for OTC)		asst. MA Marija Novičić, electrical and computer engineer asst. MA Aleksa Stojić, electrical and computer engineer
ESPB		6.0	Status	elective
Condition		none
The goal		Introducing students to the concepts of neural networks and fuzzy logic systems. Introducing different architectures, design methods, settings and implementations. Introducing applications in the field of signal processing.
The outcome		Students will be able to independently analyze and synthesize different types of neural networks and fuzzy logic systems for various engineering applications, with a special focus on signal processing. They will also learn to develop and implement such systems using modern programming environments (Matlab and Python).
Contents
URL to the subject page		https://automatika.etf.bg.ac.rs/sr/13m054nm
Contents of lectures		Development of neural networks, architecture and problems. Classification and clustering. Dynamic networks. Deep networks. Convolutional networks. LSTM. Concepts of fuzzy logic. Mamdani and Sugen's machine model. Design and tuning of fuzzy systems. Advanced techniques and synergy of neural networks and fuzzy logic. Various aspects of application in signal processing.
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
M. Nielson, Neural Networks and Deep Learning, Determination press, 2015 (Original title) Neural Networks for Pattern Recognition, Christopher Bishop, Oxford University Press, 2000 (Original title) Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville, The MIT Press, 2017 (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
3	1	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		40
Colloquia		30
Seminars		0