SYLLABUS

University: Technical University of Košice

Faculty: Faculty of Electrical Engineering and Informatics

Department: Department of Cybernetics and Artificial Intelligence

Course Number: 26000765

Course Name: Hybrid Computational Intelligence

Type, scope and method of learning activities:
Course Type: Lecture, Numerical exercises, Laboratory exercise
Recommended scope of the course content (in hours):
Full-time study (hours per week): 1,1,1
Part-time study (hours per semester): ST 13,13,13
Study Method:

Number of credits: 5

Recommended semester of study: ST

Recommended semester

Study programme

Study grade

Study Method

1.rok ST

Intelligent Systems (IS_Ing_D_sk)

Master

Attendance

Level of study: Master

Prerequisites:

Course completion requirements:
Assessment and completion of the course: Credit test and examination
Continuous assessment: Student passes the continuous assessment and receives credits when he or she meets the requirement to obtain at least 21% out of 40%.
consecutive tests, projects
Final assessment: Student passes the final assessment and passes the examination when he or she meets the requirement to obtain at least 31% out of 60%.
final test and oral examination
Overall assessment: Overall assessment is the sum of the assessments obtained by students in the assessment period. The overall result is determined in accordance with the internal regulations of the Technical University in Košice. (Study Regulations, the internal regulation principles of doctoral studies)

Learning outcomes:
A graduate gains knowledge about utilization of hybrid computational intelligence (HCI) means based on fuzzy sets, artificial neural networks and genetic algorithms for needs of modelling and control. From this reason the graduate obtains necessary theoretical knowledge about intelligent control structures, adaptation and parameter optimization methods of HCI, which contain also description, modelling, simulation, optimization and control with help of HCI means. Elaborating projects the graduate gains practical ability to develop and design own problem solutions, further to utilize obtained knowledge and to efficiently decide at choice and use of proper means. Besides, he/she learns to keep contact with development of this scientific discipline.

Brief course content:
• Role and significance of computational intelligence means hybridization.
• Main interaction types of fuzzy systems and neural networks – neuro-fuzzy and fuzzy-neuro systems and their main representatives.
• Main interaction types of fuzzy systems and evolutionary (genetic) algorithms – Michigan and Pittsburgh approach, knowledge base optimization by genetic algorithms.
• Interaction of neural networks and evolutionary (genetic) algorithms.
• Theory of chaos in optimization tasks.
• Application examples HCI means.
• General theory of uncertainty – overview of uncertainty types and mutual relations.

Recommended Reference Sources:
• Lin, Ch.T. - Lee, G.: Neural Fuzzy Systems - A Neuro-Fuzzy Synergism to Intelligent Systems; Prentice Hall PTR, New York, 1996.
• Cordón, O. at al.: Genetic Fuzzy Systems – Evolutioary Tuning and Learning of Fuzzy Knowledge Bases, World Scientific, 2001.
• Buša, J. – Hnatič, M.: Chaos – Úvod do problematiky (učebnica), Technická univerzita v Košiciach, 2004.

Recommended optional program components:

Languages required for the course completion:

Notes:

Course assessment:
Total number of students assessed: 17

41%

12%

35%

12%

Teacher:
prof. Ing. Peter Sinčák, CSc.
doc. Dr. Ing. Ján Vaščák

Last modified: 31.08.2017

Approved by: person(s) responsible for the study program