13E054VI - Artificial Intelligence

Course specification
Course title		Artificial Intelligence
Acronym		13E054VI
Study programme		Electrical Engineering and Computing
Module		Signals and Systems
Type of study		bachelor academic studies,master academic studies
Lecturer (for classes)		professor PhD Predrag Tadić
Lecturer/Associate (for practice)		professor PhD Predrag Tadić Maša Tiosavljević, electrical and computer engineer
Lecturer/Associate (for OTC)		professor PhD Predrag Tadić Maša Tiosavljević, electrical and computer engineer
ESPB		6.0	Status	elective
Condition		none
The goal		This course provides a broad technical introduction and a survey of core concepts of artificial intelligence, including search, planning, reinforcement learning, and reasoning under uncertainty. The goal is to provide students with both theoretical and practical tools to model, design and test artificial intelligence systems, with practical implementation of agents in Python.
The outcome		Students will be able to independently analyze the environment the agent is to operate in and the goals it should attain, to choose adequate artificial intelligence algorithms for the problem at hand, and to design, practically implement and test these algorithms using Python.
Contents
Contents of lectures		Search and planning: classical, local and adversarial search, constraint satisfaction problem. Reinforcement learning: Markov decision processes, state and action value functions, Q-learning, REINFORCE. Probabilistic reasoning: Bayes nets, exact and Monte Carlo inference. Temporal models: hidden Markov models, dynamic Bayes nets, particle filter.
Contents of exercises		Detailed solutions to problems which demonstrate the mechanics and important aspects of algorithms covered in lectures. Interactive demonstrations and analysis of practical implementations of these algorithms applied to illustrative problems.
Literature
Artificial Intelligence: A Modern Approach. 3rd Edition, S. Russell and P. Norvig. Prentice Hall, 2020 (Original title) R.S. Sutton, A.G. Barto. Reinforcement learning: An introduction. MIT press, 2018. (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		oral lectures, blackboard exercises, computer demonstrations
Knowledge score (maximum points 100)
Pre obligations		Points	Final exam	Points
Activites during lectures		0	Test paper	60
Practical lessons		10	Oral examination	0
Projects
Colloquia		30
Seminars		0