Course: null

» List of faculties » EF » KIN
Course title -
Course code KIN/UMI
Organizational form of instruction Lecture + Lesson
Level of course Master
Year of study not specified
Semester Winter
Number of ECTS credits 4
Language of instruction Czech
Status of course Compulsory-optional
Form of instruction Face-to-face
Work placements Course does not contain work placement
Recommended optional programme components None
  • Nejedlová Dana, Ing. Ph.D.
Course content
Lectures (topics): 1. Definition of the term artificial intelligence, research history, practical applications. 2. Representation of facts using state space, heuristics and state space search. 3. Alpha-Beta pruning state space while playing board games for two players. 4. Predicate 1st order logic. 5. Complexity of algorithms. 6. Bayes networks. 7. Decision trees. 8. Neural Networks: History, Representation of Logic Functions, Linear Separability. 9. Double Layer Neural Network: Learning with Supervision - Perceptron and Delta Rule. 10. Multilayer neural network: solution of linearly inseparable problems using backpropagation algorithm. 11. Multilayer Neural Network: Appropriate Applications and Training Methodology. 12. The Hopfield Network and Hebb's Rule for Learning. 13. Konhonen's self-organizing network: learning without supervision. 14. Genetic algorithms. Seminars (themes): 1. Representing specific tasks using state space. 2. Solving a specific task using Prolog. 3. Writing predicates. 4. Representation of specific issues by Bayes Network. 5. Representation of a specific issue by the decision tree. 6. Dynamic Time Warping algorithm. 7. Vector classification using Perceptron and Delta rules. 8. Classification of economic subjects using multilayer neural network. 9. Prediction using a multilayer neural network. 10. Utilization of Hopfield Network for Restoration of Damaged Patterns. 11. Use of Hopfield and Hebb network to determine data dependencies. 12. Use of Kohonen Network for Nonlinear Analysis of Main Components and Business Traveler Problem. 13. Programming genetic algorithm. 14. Genetic algorithm testing.

Learning activities and teaching methods
Monological explanation (lecture, presentation,briefing), Working activities (workshops)
  • Class attendance - 56 hours per semester
Learning outcomes
Students will become acquainted with modern methods of artificial intelligence as tools for decision making and management. The theoretical aspects of this subject will be linked to knowledge of algebra, programming techniques and specialized economic disciplines.


Assessment methods and criteria
Oral exam, Written exam, Practical demonstration of acquired skills, Systematické pozorování studenta, Presentation of student research activity, Written assignment

Credit requirements: Active participation in exercises. Test of theoretical knowledge. Exam: Construction of a program in any programming language solving a practical problem with artificial intelligence methods and its defence.
Recommended literature
  • ERTEL, W. Introduction to Artificial Intelligence. 2nd ed.. New York, 2017. ISBN 978-3319584867.
  • HAYKIN, S. O. Neural Networks and Learning Machines. 3rd ed.. New Jersey, 2016. ISBN 978-9332570313.
  • HEATON, Jeff. Artificial Intelligence for Humans, Volume 3: Deep Learning and Neural Networks. Chesterfield, 2015. ISBN 978-1505714340.
  • MARSLAND, Stephen. Machine Learning: An Algorithmic Perspective. Chapman & Hall/Crc Machine Learning & Pattern Recognition, 2014. ISBN 978-1466583283.
  • MAŘÍK, V., O. ŠTEPÁNKOVÁ, J. LAŽANSKÝ, et al. Umělá inteligence 1. - 6. díl. Praha: Academia, 2013. ISBN 80-200-0502-1.
  • RUSSELL, S. a P. NORVIG. Artificial Intelligence: A Modern Approach. Global Edition. 3rd ed.. Pearson, 2016. ISBN 978-1292153964.

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