Neural network technologies
Course: Computer science
Structural unit: Faculty of information Technology
            Title
        
        
            Neural network technologies
        
    
            Code
        
        
            ВК 1.5
        
    
            Module type 
        
        
            Вибіркова дисципліна для ОП
        
    
            Educational cycle
        
        
            First
        
    
            Year of study when the component is delivered
        
        
            2024/2025
        
    
            Semester/trimester when the component is delivered
        
        
            6 Semester
        
    
            Number of ECTS credits allocated
        
        
            5
        
    
            Learning outcomes
        
        
            Apply models of knowledge representation in modern information systems, process audio, video and text information and numerical data, including using neural network technologies.
        
    
            Form of study
        
        
            Full-time form
        
    
            Prerequisites and co-requisites
        
        
            Be able to perform problem analysis for structuring input and output information.
Have the skills to work in any modern instrumental programming environment, develop programs in high-level languages to implement the given task.
        
    
            Course content
        
        
            While studying the discipline, students acquire knowledge of the theoretical and practical foundations of neural network technologies; study the methods of designing and training neural networks; gain practical experience in the basics of programming artificial neural networks based on the use of modern software tools.
The discipline is aimed at forming in students the ability to design and develop software implementations of artificial neural networks for the tasks of analysis and processing of various information, decision-making, pattern recognition based on the use of existing neural network paradigms, neural network learning algorithms.
        
    
            Recommended or required reading and other learning resources/tools
        
        
            1.	Subbotin S. O. Neural networks: theory and practice: teaching. manual / S. O. Subbotin. - Zhytomyr: Vyd.O. O. Evenok, 2020. – 184 p. 
2.	Trotsky V.V. Methods of artificial intelligence: educational, methodological and practical guide. - Kyiv: University of Economics and Law "KROK", 2020 - 86 p. 
3.	Francois Chollet Deep Learning with Python, Second Edition - Manning Publications, 2021. – 386 p.
        
    
            Planned learning activities and teaching methods
        
        
            Lectures, Laboratory classes,  Student's work independently
        
    
            Assessment methods and criteria
        
        
            Student assessment is carried out from all types of work, including the study of theoretical material, laboratory work, and individual tasks, modular control works.
The maximum number of points that a student can receive for work during the semester is 60 points on a 100-point scale.
Summative assessment is an exam in written form. The overall score for the exam is 40 points on a 100-point scale. If a student receives less than 24 points during the exam, they get an "unsatisfactory" grade and the earned points are not counted.
The recommended minimum for admission to the exam is 36 points, the critically calculated minimum is 20 points. 
In order to be admitted to the exam, it is mandatory to complete all laboratory work and receive a positive assessment from the semester modular control work.
        
    
            Language of instruction
        
        
            Ukrainian
        
    Lecturers
This discipline is taught by the following teachers
Departments
The following departments are involved in teaching the above discipline