Machine Learning

The course is dedicated to the study of basic machine learning methods. The topics of the course can be divided into three blocks. The first block is about working with data and exploratory data analysis. Students will learn Python libraries for tabular data and visualization, methods of data preprocessing, including categorical and text features. The second block deals with supervised learning. The following algorithms will be discussed: linear models, decision trees, model compositions (random forest, gradient boosting and their implementations). The third block is on unsupervised learning, including clustering, visualisation, and dimensionality reduction. All topics are supported with practice on real data. By the end of the course, the students will be able to formulate a machine learning problem, select a quality metric, train a model, select hyperparameters, and validate the model.