Deep Learning

Course: Mathematical Methods of Artificial Intelligence

Structural unit: Faculty of Computer Science and Cybernetics

Title
Deep Learning
Code
ННД.02
Module type
Обов’язкова дисципліна для ОП
Educational cycle
Second
Year of study when the component is delivered
2021/2022
Semester/trimester when the component is delivered
2 Semester
Number of ECTS credits allocated
4
Learning outcomes
LO 1.1.To know the formulation of the main tasks LO 1.2. To know the basic approaches to solving problems LO.1.3To know the basic concepts and methods of machine learning
Form of study
Prerequisites and co-requisites
1. To know: the basic disciplines - "Mathematical Analysis", "Linear Algebra and Geometry", "Probability Theory and Mathematical Statistics", "Programming", "Computational Geometry and Computer Graphics", "Algorithms and Data Structures", "Machine Learning" . 2. To be able to: develop, analyze and apply algorithms and software to solve problems and applied tasks using modern software development methods.
Course content
Discipline aim. The aim of the discipline is to acquaint students with the basics of neural networks as one of the main branches of artificial intelligence, and modern methods for solving problems of machine learning, including obtaining semantic and metric information from data. To prepare the student for the effective use of modern methods such as machine learning methods to create artificial intelligence systems in further professional activities; help to acquire skills of practical work with modern software for building intelligent models.
Recommended or required reading and other learning resources/tools
1. Ian Goodfellow. Deep Learning, MIT Press, 2017 2. Richard Szeliski. Computer Vision: Algorithms and Applications, Springer, 2010 3. Dэvyd A. Forsait, Zhan Pons. Kompiuternoe zrenye. Sovremennыi podkhod, 2004 4. Lynda Shapyro, Dzhordzh Stokman. Kompiuternoe zrenye. Laboratoryia znanyi. 2013 5. Stephen Marsland. Machine Learning: An Algorithmic Perspective, 452 р., 2015. 6. Christopher M Bishop. Pattern recognition. Machine Learning, 128 p., 2006. 7. Ethem Alpaydin. Introduction To Machine Learning, 584 p., 2009. 8. Tom M. Mitchell. Machine Learning [http://www.cs.cmu.edu/~tom/mlbook.html] 9. Yaser S. Abu-Mostafa. Learning from data, 215 p., 2017 10. Alex Smola. Introduction to Machine Learning, 234 p., 2008.
Planned learning activities and teaching methods
Lecture, Laboratory work, individual work
Assessment methods and criteria
- semester examination: 1. Active work during a lection: PH1.1, PH1.2, PH1.3, PH1.4; 2. Execution of individual tasks: PH2.1, PH2.2, PH2.3; 3. Test 1: PH1.1, PH1.2; 4. Test 2: PH1.3; 5. Test 3: PH1.4; - final examination: final test. - maximum: 40 points; - studying results for examination: PH1.1, PH1.2, PH1.3, PH1.4; - task form: writing.
Language of instruction
Ukrainian language

Lecturers

This discipline is taught by the following teachers

Bohdan V Bobyl
Mathematical Informatics
Faculty of Computer Science and Cybernetics

Departments

The following departments are involved in teaching the above discipline

Mathematical Informatics
Faculty of Computer Science and Cybernetics