19M034VIM - Artificial Intelligence in Mobile Systems

Course specification
Course title		Artificial Intelligence in Mobile Systems
Acronym		19M034VIM
Study programme
Module
Type of study
Lecturer (for classes)		professor PhD Aleksandar Nešković
Lecturer/Associate (for practice)		professor PhD Aleksandar Nešković asst. MA Jelena Mladenović, electrical and computer engineer asst. MA Marko Burdžić, electrical and computer engineer
Lecturer/Associate (for OTC)		MA Kristina Jovičić, electrical and computer engineer asst. MA Jelena Mladenović, electrical and computer engineer asst. MA Marko Burdžić, electrical and computer engineer
ESPB		6.0	Status	elective
Condition		Radio Systems
The goal		Mobile networks are part of our everyday lives, whereas the use of AI is growing rapidly. The goal of this course is to provide students with an introduction to problems and techniques of AI. In a step-by-step manner, the following AI techniques are introduced: supervised , unsupervised and reinforcement learning. It explains how these techniques can be used for future wireless networks.
The outcome		Student who completes this course is expected to: * understands the basic concepts of various techniques of artificial intelligence, * understands the possibility of applying machine learning in different segments of a mobile network, * master the basic algorithms and software tools for applying the techniques of machine learning to specific problems.
Contents
Contents of lectures		Overview of basic concepts of artificial intelligence and machine learning. Basic types of machine learning (unsupervised, reinforcement, supervised). Classification, regression, clustering. Validation methods. Overfitting problem. Examples of applications from the mobile systems domain.
Contents of exercises		The students will have several programming projects.
Literature
Haesik Kim, Artificial Intelligence for 6G, Springer International Publishing, 2022 (Original title) Yuanming Shi, Kai Yang, Zhanpeng Yang, Yong Zhou, Mobile Edge Artificial Intelligence Opportunities and Challenges, Elsevier, 2021. (Original title) Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016.god (Original title) Hassoun M., Fundamentals of Artificial Neural Networks. Massachusetts MA: The MIT Press; 2003. (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		The students will have several programming projects.
Knowledge score (maximum points 100)
Pre obligations		Points	Final exam	Points
Activites during lectures			Test paper	30
Practical lessons			Oral examination
Projects
Colloquia
Seminars		70