Artificial intelligence
0800-SZIN
1. Introduction to AI methods: key AI issues; AI status; fifth generation of computers and other great projects.
2. Search: problem representation in the state space; reduction representation; search methods; examples of search-based programs; searching and human thinking.
3. Knowledge representation: types of knowledge; state representation; logical representation - predicate logic, fuzzy, approximate; procedural representation; semantic networks; production systems; frames and scripts.
4. Understanding of natural language: machine translation; grammar; text generation; examples of programs.
5. Advisory systems: knowledge acquisition; construction of expert systems; examples of applications.
6. Mind models and the most ambitious AI projects: CyC system; unified theories of cognition and SOAR;
7. Cognitive computer science - IBM Watson, human cognitive architecture.
8. Machine learning and knowledge discovery in data.
Total student workload
30 h lectures + 24 h labs + 60 h own work on assigned projects, plus 30 hours of preparation for exam
Learning outcomes - knowledge
After completion of the course, exam and lab assignments students should be able to:
* define, describe and present topics related to artificial intelligence, concepts and basic methods (K_W08);
* know how to estimate computational complexity of various search algorithms (K_W04);
* knows basic methods of knowledge representations and inference schemes (K_W08);
* understands challenges and methods applied to natural language processing;
* knows basic principles of expert systems and their possible use;
* understands methods of design, tools used for creation of AI systems and potential of AI applications in various domains (K_W08).
Learning outcomes - skills
After completion of the course, exam and lab assignments students should be able to:
• find and critically assess information in the Internet and in scientific
and popular science journals related to the AI (K_U04);
• use theoretical knowledge about concepts useful for analysis of problems together with appropriate methods of knowledge representation, depending on the application (K_U02);
• estimate possibilities and choose appropriate methods for creating models constructing expert systems, depending on the field of applications (K_U01, K_U02);
• find interesting AI tools that may be used to help in scientific research (K_U04).
Learning outcomes - social competencies
After completion of the course, exam and lab assignments students should be able to:
* be able to implement with success projects that require programming and application of methods learned (K_K03)
* present in an understandable way information about computer algorithms, methods of informatics, understand the need to follow scientific literature to catch up with rapid progress in this field (K_K04);
* understand the importance of the knowledge gained, evaluate it in critical way and know its limits (K_K06).
Teaching methods
Lectures + lab + demonstrations of programs + own projects.
Expository teaching methods
- problem-based lecture
- informative (conventional) lecture
Exploratory teaching methods
- laboratory
- project work
Type of course
compulsory course
Prerequisites
Basic programming course
Course coordinators
Assessment criteria
Evaluation of lab projects.
Written examination, max 10 points,
Points 10 9 8 7 6 5 4.5 1-4
Marks 5 4+ 4 4- 3+ 3 3- 2
Practical placement
Bibliography
• Russel & Norvig: AI - the modern approach.
MOOC courses.
Additional information
Additional information (registration calendar, class conductors,
localization and schedules of classes), might be available in the USOSweb system: