Course: Introduction to Artificial Intelligence

» List of faculties » FEK » KMI
Course title Introduction to Artificial Intelligence
Course code KMI/UUI
Organizational form of instruction Lecture
Level of course unspecified
Year of study not specified
Semester Winter
Number of ECTS credits 4
Language of instruction Czech
Status of course unspecified
Form of instruction unspecified
Work placements This is not an internship
Recommended optional programme components None
Lecturer(s)
  • Beránek Ladislav, prof. Ing. CSc., MBA
Course content
1. General introduction to artificial intelligence - technology overview 2. Basic concepts of machine learning 3. Machine learning - overview of algorithms 3. Neural networks - basic concepts 4. Other types of neural networks, convolutional neural networks 5. Graph neural networks, Node2Vec 6. Feedback learning 7. Word processing, Word2Vec 8. Image recognition 9. Other applications of neural networks 10. Technology Agents 11. Selected applications in economics

Learning activities and teaching methods
Monologic (reading, lecture, briefing), Demonstration, Work with multi-media resources (texts, internet, IT technologies)
  • Class attendance - 20 hours per semester
  • Preparation for classes - 20 hours per semester
  • Preparation for credit - 20 hours per semester
  • Semestral paper - 28 hours per semester
  • Preparation for exam - 24 hours per semester
Learning outcomes
Identification and characterization of artificial intelligence, the formulation of the background and basic problems of the field of artificial intelligence. The concept of an intelligent system, modeling of intelligent systems, the use of simulation in system design, working with uncertain and incomplete information, the foundations of soft computing, agent and multiagent architectures, learning adaptive systems, reinforcement learning, planning applications. The main focus is the use of neural networks in these technologies.
By completing the course students acquire basic overview of the issues covered in artificial intelligence as well as methods for their solution. Emphasis is focused on developing the student's ability to solve practical problems with the use of neural networks.
Prerequisites
Subjects MATI, MATII. Knowledge of programming in a programming language, e.g. Python
KMI/CM1
----- or -----
KMI/KMATI
----- or -----
KMI/MATI
----- or -----
KMI/M1 and KMI/CM2
----- or -----
KMI/KMATA
----- or -----
KMI/KMIIA
----- or -----
KMI/KMTII
----- or -----
KMI/MAIIA
----- or -----
KMI/MATIA
----- or -----
KMI/MATII
----- or -----
KMI/M1A
----- or -----
KMI/M2
----- or -----
KMI/M2A
----- or -----
KMI/YMAII
----- or -----
KMI/YMATI

Assessment methods and criteria
Test

Requirements on students: Processing of assignments during the semester Pass the final written test - - solving the assigned task
Recommended literature
  • Ferber, J. Multi-Agent Systems. London, Adisson-Wesley, 1999.
  • Mařík, V. a kol. Umělá inteligence 1-4. Praha, Academia, 1993.
  • Russel, S., Norvig, P. Artificial Intelligence, a Modern Approach. Pearson Education Inc., 2003.
  • Stevens, E., Antiga, L. and Viehmann, T. Deep Learning with PyTorch: Build, train, and tune neural networks using Python tools. Boston: Manning. 2020.
  • Sutton, R.S., Barto, A.G. Reinforcement Learning - An Introduction. Cambridge, The MIT Press, 1992.
  • Wooldridge, M. Reasoning about Rational Agents. Cambridge, The MIT Press, 2000.


Study plans that include the course
Faculty Study plan (Version) Category of Branch/Specialization Recommended year of study Recommended semester