Machine Learning Methods

Entry requirements: Basic knowledge of probability theory and mathematical statistics, programming skills.

Credits: 5

Course: Core

Language of the course: Russian


  • To get familiar with main tasks and methods of machine learning and intelligent data analysis.
  • To study statistical foundations of machine learning theory
  • To learn how to solve tasks of classification, regression, clustering with the use of methods and algorithms of machine learning and to evaluate the quality of these solutions
  • To implement machine learning software to solve domain-specific tasks


The course combines training in statistical theory of machine learning with hands-on experience in applying efficient algorithms of machine learning to solve domain-specific tasks. The course is divided in three sections covering methods of classification and regression, unsupervised learning, as well as neural networks. Students will be able to retrieve knowledge relevant to professional activity in any area that is linked to gathering and processing large amounts of data.


Lectures, labs and practice sessions


Attendance is mandatory. Students can not miss more than one class without prior warning. Admission to the final exam is based on completion of all laboratory assignments. The final grade is based on the student performance throughout the course.