At the end of learning this discipline, a student should be able to demonstrate the following study results:
1) knowledge of theoretical foundations of artificial neural networks;
2) ability to apply existing methods of building artificial neural networks;
3) ability to use principles of mathematical modeling of analog neural networks;
4) ability to apply methodology of mathematical modeling digital neural networks;
5) ability to use methods of stability investigation of artificial neural networks;
6) ability to apply artificial neural networks.
Study of the discipline implies shaping and development the following student competencies:
general:
1) ability to study;
2) ability to communicate orally and in written form in Ukrainian and English;
3) ability to perform search and analyze an information from different sources;
4) ability to identify, formulate and solve problems;
5) ability to apply knowledge in practical situations;
6) ability to make justified decisions;
7) ability to fulfill investigations on appropriate level;
8) ability to work in command;
9) knowledge and understanding of subject area and understanding profession;
10) ability to communicate with non-professional of the same field;
11) ability to think abstractly, analyze and synthesize;
12) ability to develop and manage projects;
13) ability to work on one’s own;
14) skills of using information and communication technologies;
professional:
1) ability to use principles of building and analysis of artificial neural networks;
2) ability to use artificial neural networks.
3) ability of flexible thinking mode, that gives a possibility to understand and solve tasks keeping critical concern to steady scientific conceptions;
4) ability to use deep theoretical and fundamental knowledge in the field of information technologies for developing complex systems;
5) ability to formulate, analyze and synthesize solutions of scientific problems on abstract level by their decomposition on parts which can be investigated separately in their more and less important aspects;
6) ability to build models of complex information systems, conduct their investigation for building projects of systems;
7) ability to develop and implement models of information systems by using tools of computer modeling;
8) ability to communicate with colleagues from given area concerning scientific achievements as on general level as on the level of specialist;
9)ability to make oral and written reports, discuss scientific subjects in native language and in English;
10) ability to make oral presentation and write clear paper based on results of fulfilled investigations;
11) ability to formulate (making presentations or reports) new hypotheses and scientific tasks in the area of information technologies, choose relevant directions and corresponding methods for their solving;
12) ability to accept obtained knowledge in the area of computer sciences, information technologies and integrate their into available ones;
13) ability to study and evaluate critically new information technologies, models and methods having grounded on professional in these areas scientific literature sources.

• prerequisite: differential equations; numerical methods; theory of systems; theory of electronic circuits; programming languages, algorithms and data structures; computer networks;
• co-requisite: systems of artificial intelligence; signal processing; distributed computer systems.

Basics of theory of artificial neural networks and some their applications are studied, in particular: mathematical foundations of artificial neural networks; their architecture and electronic realization; stability of functioning networks; networks of linear, quadratic programming and linear complementary problems, algorithms of optimization without limitations and learning algorithms; the networks of nonlinear optimization problems with limitations; the networks of discrete and combinatorial optimization, the networks of identification of signals and systems; methods of modeling neural oscillators.

Basic
1. А. Cichocki and R. Unbehauen, Neural Networks for Optimization and Signal Processing, John Wiley and Sons, 1993.
2. S. Haykin. Neural Networks: A Comprehensive Foundation, Prentice-Hall, Upper Saddle River, New Jersey, 1999.
3. Руденко О. Г., Бодянський Є. В. Штучні нейронні мережі: Навчальний посібник. – Харків: ТОВ ”Компанія СМІТ”, 2006. – 404 с.
4. Тимощук П. В. Штучні нейронні мережі: навч. посібник / П. В. Тимощук. – Львів: Видавництво Львівської політехніки, 2011. – 444 с.
Complementary
1. R.M. Golden, Mathematical Methods for Neural Network Analysis and Design: MIT Press, Cambridge, Massachusetts, 1996.
2. Глибовець М.М., Олецький О.В. Штучний інтелект. - К .:Видавничий дім "КМ Академія" , 2002 . - 366 c.
Information Resource
Тимощук П. В., Кривий Р. З. Штучні нейронні мережі: Електронний навчально-методичний комплекс для студентів Інституту комп’ютерних наук та інформаційних технологій спеціальності 8.05010102 “Інформаційні технології проектування”. Сертифікат № 00473, номер та дата реєстрації: Е41-165-32/2013 від 28.10.2013 р. [Електронний ресурс] – Режим доступу: http://vns.lp.edu.ua/course/view.php?id=8582.

• current control (50%): current reports of laboratory works, oral asking;
• final control (50%, examination): fulfilling test tasks.