Course: Artificial and Computational Intelligence I

« Back
Course title Artificial and Computational Intelligence I
Course code USII/PUVI1
Organizational form of instruction Lecture + Tutorial
Level of course Master
Year of study 1
Semester Winter
Number of ECTS credits 5
Language of instruction Czech
Status of course Compulsory
Form of instruction Face-to-face
Work placements This is not an internship
Recommended optional programme components None
Lecturer(s)
  • Hájek Petr, prof. Ing. Ph.D.
  • Olej Vladimír, prof. Ing. CSc.
Course content
Fuzzy inference systems. The Mamdani fuzzy inference system design. The Takagi-Sugeno fuzzy inference system design. Neural networks key concepts. The division of object sets to training and testing sets. Neural networks models. The process of neural networks study. Designing models for economics processes classification and prediction using neural networks. Evolutionary stochastic optimising algorithms. Optimising using genetic algorithms. Neuro-fuzzy-genetic systems. Using artificial and computational intelligence in decision-support and management.

Learning activities and teaching methods
Monologic (reading, lecture, briefing), Dialogic (discussion, interview, brainstorming), Laboratory work
Learning outcomes
The aim of the course is to provide knowledge of the model design in the field of artificial and computer intelligence and of the possibilities of their application to different areas of social life, especially the economics, social and environmental spheres.
The students should be able to design fuzzy inference systems for classification and prediction, especially in the economics, social and environmental spheres, as well as to design models based on neural and fuzzy neural networks.
Prerequisites
unspecified

Assessment methods and criteria
Oral examination, Written examination, Didactic test, Discussion, Class observation

Completion and successful defence of two projects with a success rate of at least 60 %, written tests throughout the semester. The assignment grade consists of 50 % project result and 50 % written test result. The examination is written.
Recommended literature
  • KUNCHEVA, L. I. Fuzzy Classifier Design. A Springer Verlag Company, Germany, 2000. ISBN 80-903024-9.
  • KVASNIČKA, V. a kol. Úvod do teórie neurónových sietí.. Bratislava: IRIS, 1997. ISBN 80-88778-30-1.
  • OLEJ V. Modelovanie ekonomických procesov na báze výpočtovej inteligencie.. Miloš Vognar - M&V, Hradec Králové, 2003. ISBN 80-903024-9-1.
  • Olej, Vladimír. Úvod do umělé inteligence : moderní přístupy : distanční opora. Pardubice: Univerzita Pardubice, 2010. ISBN 978-80-7395-307-2.
  • Olej, Vladimír. Úvod do umělé inteligence. Pardubice: Univerzita Pardubice, 2009. ISBN 978-80-7395-241-9.


Study plans that include the course
Faculty Study plan (Version) Category of Branch/Specialization Recommended year of study Recommended semester
Faculty: Faculty of Economics and Administration Study plan (Version): Insurance Engineering (2013) Category: Economy 1 Recommended year of study:1, Recommended semester: Winter
Faculty: Faculty of Economics and Administration Study plan (Version): Regional and Information Management (2014) Category: Economy 1 Recommended year of study:1, Recommended semester: Winter
Faculty: Faculty of Economics and Administration Study plan (Version): Insurance Engineering (2014) Category: Economy 1 Recommended year of study:1, Recommended semester: Winter
Faculty: Faculty of Economics and Administration Study plan (Version): Informatics in Public Administration (2013) Category: Economy 1 Recommended year of study:1, Recommended semester: Winter
Faculty: Faculty of Economics and Administration Study plan (Version): Regional and Information Management (2013) Category: Economy 1 Recommended year of study:1, Recommended semester: Winter
Faculty: Faculty of Economics and Administration Study plan (Version): Informatics in Public Administration (2014) Category: Economy 1 Recommended year of study:1, Recommended semester: Winter