Artificial Intelligence
Niveau
Master's degree program
Learning outcomes of the courses/module
The participants:
• can describe different strategies for implementing artificially intelligent systems
• can understand the advantages and disadvantages of the strategies they have studied and can identify their challenges
• can develop strategies for designing artificially intelligent systems for practical use
• can describe different strategies for implementing artificially intelligent systems
• can understand the advantages and disadvantages of the strategies they have studied and can identify their challenges
• can develop strategies for designing artificially intelligent systems for practical use
Prerequisites for the course
No prerequisites
Course content
The following topics are covered in the course:
- Reasoning approaches (goal trees, rule-based expert systems)
- Search approaches (depth-first, hill climbing, beam, optimal, branch and bound, A*, games, minimax, and alpha-beta)
- Constraint approaches (search, domain reduction, visual object recognition)
- Learning approaches (neural nets, back propagation, genetic algorithms, sparse spaces, phonology, near misses, felicity conditions, support vector machines, boosting)
- Representation approaches (classes, trajectories, transitions)
- Applications of artificial intelligence in various contexts
- Weak versus strong artificial intelligence
- Reasoning approaches (goal trees, rule-based expert systems)
- Search approaches (depth-first, hill climbing, beam, optimal, branch and bound, A*, games, minimax, and alpha-beta)
- Constraint approaches (search, domain reduction, visual object recognition)
- Learning approaches (neural nets, back propagation, genetic algorithms, sparse spaces, phonology, near misses, felicity conditions, support vector machines, boosting)
- Representation approaches (classes, trajectories, transitions)
- Applications of artificial intelligence in various contexts
- Weak versus strong artificial intelligence
Recommended specialist literature
- Russell, S.; Norvig, P. (2021): Artificial Intelligence: A Modern Approach, Global Edition (Ed. 4), Addison Wesley, Boston (ISBN: 978-1292401133)
- Rissover, M. N. (2025): Artificial Intelligence: A Practical Guide to Understanding AI for Professionals and Students (Ed. 1), Digital Foundations, (ISBN: 979-8286961795)
- Rissover, M. N. (2025): Artificial Intelligence: A Practical Guide to Understanding AI for Professionals and Students (Ed. 1), Digital Foundations, (ISBN: 979-8286961795)
Assessment methods and criteria
Written exam
Language
English
Number of ECTS credits awarded
4
Semester hours per week
Planned teaching and learning method
The following methods are used:
- Lecture with discussion
- Interactive workshop
- Lecture with discussion
- Interactive workshop
Semester/trimester in which the course/module is offered
3