13E054NM - Neural Networks

Course specification
Course title		Neural Networks
Acronym		13E054NM
Study programme		Electrical Engineering and Computing
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 asst. professor PhD Sanja Vujnović asst. Aleksa Stojić, electrical and computer engineer
Lecturer/Associate (for OTC)		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 technology, different architectures, internal and external signal representation, learning ability and distributed information processing capability. Design neural network systems for typical engineering applications, including algorithms for signal processing, classification, regression, knowledge extraction.
The outcome		Students will be able to independently analyze and synthesize different types of neural networks that are applied in many areas of engineering and learn to apply various algorithms for learning and training of neural networks and their implementation using MATLAB and Neural Network toolbox
Contents
URL to the subject page		https://automatika.etf.bg.ac.rs/sr/13e054nm
URL to lectures		https://teams.microsoft.com/l/team/19%3aA7XKjG47iuR_1XzyaGLls2ZRFB_X5LiWKnP391HqCK81%40thread.tacv2/conversations?groupId=3adb00c5-eb90-44f6-a500-18bd7fb3f8ca&tenantId=1774ef2e-9c62-478a-8d3a-fd2a495547ba
Contents of lectures		Neural network history and types of problems: function approximation, classification, data clustering, time series, and dynamic systems modelling. Backpropagation algorithm, generalization, overfitting and initialization. Convergence properties of the BP algorithm. Modeling of time series and dynamic systems using nonlinear NN, classification and clustering, NN classifiers.CNN. Deep learning.
Contents of exercises		Computer exercises with demonstrations and training algorithms for the design of neural networks. Solve practical problems in various fields of engineering with the help of neural networks using MATLAB Neural Networks toolbox.
Literature
Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems, Chin-Teng Lin, C. S. George Lee, Prentice Hall, 1996 Neural Networks: A Comprehensive Foundation, 2nd edition. Simon Haykin, Prentice Hall, 1998 Neural Networks for Pattern Recognition, Christopher Bishop, Oxford University Press, 2000 Handbook of Neural Network Signal Processing, Ed. by Yu Hen Hu and Jenq-Neng Hwang, CRC Press, 2002 M. Nielson, Neural Networks and Deep Learning, Determination press, 2015
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
Colloquia		40
Seminars		30