Infopaket

Technologies of computational intelligence

ОК.6

Обов’язкова дисципліна для ОП

Second

2021/2022

9 Semester

5

Conduct research in the field of computer science. Develop new algorithms for solving problems in the field of computer science, and evaluate their effectiveness and limitations on their application. Know the principles of construction, composition, and architecture of computer systems for pattern recognition, and use methods for their design. Be able to apply methods and tools for pattern recognition. Know the principles of building models and methods of computational intelligence, neural networks, fuzzy systems, genetic algorithms, and evolutionary strategies, and make a selection of models and methods for solving optimization problems using metaheuristics.

Full-time form

Know the basic concepts of mathematical analysis, linear algebra and analytical geometry, discrete mathematics, mathematical logic, informatics, programming, computational mathematics, probability theory, mathematical statistics, optimization theory, and artificial intelligence systems. Be able to apply this knowledge in the development of information systems. Possess basic ICT competencies - have skills in the practical application of communication and information technologies.

The discipline provides an opportunity to become familiar with computational intelligence methods, including fuzzy logic, artificial neural networks, and evolutionary computation, as well as their practical application. The discipline aims to develop the ability to understand the correspondence between practical problems and intellectual methods for their solution, and to create practical applications based on hybrid intelligent computation.

1. Prokhorova O. M., N. V. Kalchuk. Models and methods of fuzzy logic: educational manual. National Aerospace University named after N. E. Zhukovsky "KhAI", 2021. 166 p. 2. Razhivin, O. V. Synthesis of fuzzy controllers in automatic control systems: educational manual / O. V. Razhivin, O. V. Subotin. – Kramatorsk: CTRI "Printing House", 2017. – 212 p. 3. Subbotin, S. O. Neural networks: educational manual / S. O. Subbotin, A. O. Oliynyk; under general ed. of Prof. S. O. Subbotin. – Zaporizhzhya: ZNTU, 2014. – 132 p. 4. N. I. Boyko, V. Yu. Mykhaylyshyn. Efficiency of applying genetic algorithms for searching optimized solutions // Information systems and networks, 2016, №854. – p. 249-257. 5. Kononyuk A.Yu. Neural networks and genetic algorithms - Kyiv: "Korniychuk", 2008. – 446 p.

Lectures, laboratory classes, individual work.

The level of achievement of all planned learning outcomes is determined by the results of written tests and the completion of independent work. The maximum number of points a student can earn for work during the semester does not exceed 60 points on a 100-point scale. The final assessment is conducted in the form of an exam. The maximum number of points a student can obtain is 40 points on a 100-point scale. If a student receives less than 24 points during the exam, they are given an "unsatisfactory" grade, and the earned points are not counted. A student is not allowed to take the exam if they have scored less than 36 points during the semester (less than 60% of the maximum possible number of points a student can earn for their work during the semester).

Ukrainian