|
|
Main menu for Browse IS/STAG
Course info
KIV / UIR-E
:
Course description
Department/Unit / Abbreviation
|
KIV
/
UIR-E
|
Academic Year
|
2023/2024
|
Academic Year
|
2023/2024
|
Title
|
AI and Pattern Recognition
|
Form of course completion
|
Exam
|
Form of course completion
|
Exam
|
Accredited / Credits
|
Yes,
6
Cred.
|
Type of completion
|
Combined
|
Type of completion
|
Combined
|
Time requirements
|
Lecture
3
[Hours/Week]
Tutorial
2
[Hours/Week]
|
Course credit prior to examination
|
Yes
|
Course credit prior to examination
|
Yes
|
Automatic acceptance of credit before examination
|
No
|
Included in study average
|
YES
|
Language of instruction
|
English
|
Occ/max
|
|
|
|
Automatic acceptance of credit before examination
|
No
|
Summer semester
|
0 / -
|
0 / -
|
4 / 43
|
Included in study average
|
YES
|
Winter semester
|
0 / -
|
0 / -
|
0 / -
|
Repeated registration
|
NO
|
Repeated registration
|
NO
|
Timetable
|
Yes
|
Semester taught
|
Summer semester
|
Semester taught
|
Summer semester
|
Minimum (B + C) students
|
10
|
Optional course |
Yes
|
Optional course
|
Yes
|
Language of instruction
|
English
|
Internship duration
|
0
|
No. of hours of on-premise lessons |
|
Evaluation scale |
1|2|3|4 |
Periodicity |
každý rok
|
Evaluation scale for credit before examination |
S|N |
Periodicita upřesnění |
|
Fundamental theoretical course |
No
|
Fundamental course |
No
|
Fundamental theoretical course |
No
|
Evaluation scale |
1|2|3|4 |
Evaluation scale for credit before examination |
S|N |
Substituted course
|
None
|
Preclusive courses
|
KIV/UIR and KKY/UI
|
Prerequisite courses
|
N/A
|
Informally recommended courses
|
N/A
|
Courses depending on this Course
|
N/A
|
Histogram of students' grades over the years:
Graphic PNG
,
XLS
|
Course objectives:
|
Students acquire basic methods and techniques used in main areas of artificial intelligence - problem solving, fundamentals of logic and logic programming, knowledge representation and knowledge systems, recognition methods and their applications.
|
Requirements on student
|
Credit - Students have to obtain a minimum amount of points from a seminar work and from a written test (60%).
Examination - A written examination. It is necessary to obtain a minimum amount of points (60%).
Due to the continuous updating of the course, approval from the course guarantor is required to obtain credit when re-enrolling in the course (see Article 24, Paragraph 3).
Notice:
The dates and form of verification for fulfilling the requirements may be adjusted in light of measures announced in connection with the development of the epidemiological situation in the Czech Republic.
|
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
|
Activities
|
|
Fields of study
|
|
Guarantors and lecturers
|
|
Literature
|
-
Recommended:
Russell, Stuart J., Norvig, Peter. Artificial intelligence : A modern approach. 2nd ed. Prentice Hall, N.J., 2003. ISBN 0-13-080302-2.
-
Recommended:
Lukasová, Alena. Formální logika v umělé inteligenci. Vyd. 1. Brno : Computer Press, 2003. ISBN 80-251-0023-5.
-
Recommended:
Kubík, A. Inteligentní agenty - tvorba aplikačního software na bázi multiagentových systémů. Brno, 2007.
-
Recommended:
Nilsson, Nils J. Principles of Artificial Intelligence. Springer Verlag, Berlin, 1982.
-
Recommended:
Mařík, Vladimír. Umělá inteligence (1). Academia, Praha, 1993. ISBN 80-200-0496-3.
-
Recommended:
Mařík, Vladimír a kol. Umělá inteligence (2). Academia, Praha, 1997.
-
Recommended:
Mařík, Vladimír a kol. Umělá inteligence (3). Academia, Praha, 2001.
-
Recommended:
Mařík, Vladimír a kol. Umělá inteligence (4). Academia, Praha, 2003.
-
Recommended:
V. Mařík, O. Štěpánková, J. Lažanský a kol. Umělá inteligence (5). 2007.
-
On-line library catalogues
|
Time requirements
|
All forms of study
|
Activities
|
Time requirements for activity [h]
|
Preparation for laboratory testing; outcome analysis (1-8)
|
20
|
Contact hours
|
39
|
Preparation for an examination (30-60)
|
40
|
Preparation for formative assessments (2-20)
|
10
|
Practical training (number of hours)
|
26
|
Presentation preparation (report) (1-10)
|
5
|
Team project (50/number of students)
|
16
|
Total
|
156
|
|
Prerequisites
|
Knowledge - students are expected to possess the following knowledge before the course commences to finish it successfully: |
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
|
Knowledge - knowledge resulting from the course: |
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. |
|
Assessment methods
|
Knowledge - knowledge achieved by taking this course are verified by the following means: |
Combined exam |
Test |
Skills demonstration during practicum |
Individual presentation at a seminar |
|
Teaching methods
|
Knowledge - the following training methods are used to achieve the required knowledge: |
Interactive lecture |
Laboratory work |
E-learning |
Skills demonstration |
Self-study of literature |
|
|
|
|