|
Lecturer(s)
|
-
Král Pavel, Doc. Ing. Ph.D.
|
|
Course content
|
1. Introduction - basic concepts, motivation, (a little) history 2 - 3. Problem solving: uninformed and informed methods 4. Games, task decomposition, AND/OR graphs, evolutionary and genetic algorithms 5. Classification, recognition, clustering and regression - basic concepts 6. Feature-based recognition methods 7. Structural recognition methods 8. Neural networks 9. Introduction to knowledge representation 10. Nervous system, brain, senses, memory, language and speech 11. Intelligent agents 12. Natural language processing 13. Summary, discussion
|
|
Learning activities and teaching methods
|
Interactive lecture, E-learning, Laboratory work, Skills demonstration, Students' self-study, Self-study of literature
- Preparation for laboratory testing; outcome analysis (1-8)
- 20 hours per semester
- Contact hours
- 39 hours per semester
- Preparation for an examination (30-60)
- 40 hours per semester
- Team project (50/number of students)
- 16 hours per semester
- Practical training (number of hours)
- 26 hours per semester
- Presentation preparation (report) (1-10)
- 5 hours per semester
- Preparation for formative assessments (2-20)
- 10 hours per semester
|
| prerequisite |
|---|
| Knowledge |
|---|
| Good knowledge of mathematical analysis, linear algebra, probability theory, and mathematical statistics. Students should be able to study specialized literature and recommended computer resources (manuals, Web pages etc.) and to create special program modules in higher programming languages (Java, C, C#, Prolog,...). |
| learning outcomes |
|---|
| The student obtains after the completion of this subject: - basic knowledge about the artificial intelligence methods, methods of problem solving and recognition or classification methods, - capabilities of efective use of techniques and programming tools for software development with the aim to create a specialized software for simulation and solving above mentioned methods, - capabilities to propose simple logic systems and to verificate their features, to study the theory of logic systems and the implementation of such systems in specialized programming languages, - capabilities to propose and develope knowledge based systems and procedures for knowledge derivation using the standard database systems, - capabilities to apply modern systems for problem solving tasks (evolutionary and genetic algorithms, intelligent agents, modern software development techniques), to realize of such systems and verificate their properties. |
| teaching methods |
|---|
| Interactive lecture |
| Laboratory work |
| E-learning |
| Skills demonstration |
| Self-study of literature |
| assessment methods |
|---|
| Combined exam |
| Test |
| Skills demonstration during practicum |
| Individual presentation at a seminar |
|
Recommended literature
|
-
Kubík, A. Inteligentní agenty - tvorba aplikačního software na bázi multiagentových systémů. Brno, 2007.
-
Lukasová, Alena. Formální logika v umělé inteligenci. Vyd. 1. Brno : Computer Press, 2003. ISBN 80-251-0023-5.
-
Mařík, Vladimír a kol. Umělá inteligence (2). Academia, Praha, 1997.
-
Mařík, Vladimír a kol. Umělá inteligence (3). Academia, Praha, 2001.
-
Mařík, Vladimír a kol. Umělá inteligence (4). Academia, Praha, 2003.
-
Mařík, Vladimír. Umělá inteligence (1). Academia, Praha, 1993. ISBN 80-200-0496-3.
-
Nilsson, Nils J. Principles of Artificial Intelligence. Springer Verlag, Berlin, 1982.
-
Russell, Stuart J., Norvig, Peter. Artificial intelligence : A modern approach. 2nd ed. Prentice Hall, N.J., 2003. ISBN 0-13-080302-2.
-
V. Mařík, O. Štěpánková, J. Lažanský a kol. Umělá inteligence (5). 2007.
|