Intelligent Systems 500-KS1-3SIN5
Study profile: general
Study form: full-time
Type of course: obligatory
Scientific domain / discipline: humanities / philosophy, social communication and media
Year/semester: 3/5
Lecture: 30 h
Didactic methods: lecture, individual consulting with the teacher.
ECTS: 2
Balance of a student's labour input:
participation in lectures -- 30 h
individual consulting with teachers -- 2 h
getting acquainted with the literature -- 15 h
preparation to the classes -- 3 h
preparation to passing of the lecture -- 12 h
passing of the lecture -- 2 h
Quantitative indices:
activities requiring of a direct participation of the teacher: 34 h, 1 ECTS
Type of course
Mode
Prerequisites
Course coordinators
Learning outcomes
The graduate knows and understands:
- basic information technologies used to support cognitive and communication processes: KP_WG2;
- methods of artificial intelligence used in modelling and analysis of cognitive and communication systems: KP6_WG3.
The graduate can use information technologies and tools of information acquisition and support of cognitive and communication processes: KP_UW7.
The graduate is prepared:
- to be open to new trends in intelligent systems and to ask for experts' opinions on solving cognitive and practical problems: KP6_KK2;
- to improve the professional skills and to raise the personal competences, including the ethical ones: KP6_KR1;
- to choose methods appropriate for realization of practical, cognitive, and communication tasks: KP6_KR3;
- to apply the acquired knowledge and skills in solving problems in connection with professional practice, according to ethical rules of the profession and care about the professional achievements and tradition: KP6_KR4.
The methods of verification of the achievements: a written test, a written elaboration of tasks.
Assessment criteria
Methods of teaching / learning: lectures with use of multimedial presentations, discussion. A written or oral passing in the form of a test or elaboration of tasks. The necessary condition for the positive passing of the subject is obtaining at least 3.0 (at least 51% points obtained at the passing).
In the case of absence, students have to catch up on classes themselves.
Bibliography
1. Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning. MIT Press, 2016.
2. Patterson, J., Gibson, A., Deep Learning: A Practitioner’s Approach, O’Reilly Media, 2017.
3. Russell, S. J., Norvig, P., Artificial Intelligence: A Modern Approach, 3rd Ed., Pearson, 2014.
4. Rutkowski, L., Computational Intelligence. Methods and Techniques, Springer-Verlag, Berlin Heidelberg 2008.
5. Internet sources relevant to the field of intelligent systems.
Additional information
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: