Unsupervised Machine Learning

We invite you to the new Unsupervised Machine Learning course, which will expand your knowledge of basic machine learning methods with manual feature design, namely methods such as principal component method, k-means method, Gaussian mixture model, kernel density estimation, etc. You will also learn how to select and train classification, regression, and clustering algorithms on unlabeled data.

Level: medium

Language: English

Format: online

Course duration: 30 hours (1 ECTS)

Availability: self-study based on video and text materials on the KAU online platform with tests for each topic;

Target audience: students and postgraduates majoring in computer science, applied physics, materials science.

Registration.

Lecturers:

• Dr. Vitaliy Tymchyshyn, Junior Research Fellow at Kyiv Academic University (KAU), Junior Research Fellow at Bogolyubov Institute of Theoretical Physics (BITP);
• Dr. Volodymyr Bezguba, Senior Research Fellow at KAU, Head of KAU Laboratory of Data Science and Machine Learning;

You can meet the lecturer and learn what to expect from the course in this video

Required knowledge

Basic knowledge of higher mathematics and programming acquired during the bachelor's degree. Basic knowledge of Python.

Learning outcomes

Knowledge of the basic methods of machine learning with manual construction of features, namely such methods as: principal component analysis (PCA), k-means clustering, Gaussian mixture models, kernel density estimation, etc.

Ability to select and train classification, regression and clustering algorithms on unlabeled data.

The course is free. After its completion, all participants who complete the program and pass the tests will receive certificates with 1 ECTS credit.

The Deep Tech courses are delivered to you by the Kyiv Academic University as a part of the BOOSTalent project.