Master 2024/2025

Generative Models in Machine Learning

Type: Elective course (Math of Machine Learning)

When: 2 year, 1 module

Open to: students of one campus

Language: English

Course Syllabus

Abstract

Deep generative models are widely used in many areas of applied machine learning. In this course, we will look at modern architectures of generative models and learning algorithms. The lectures will highlight the main approaches proposed, and analyze their main advantages and disadvantages. The seminars will cover examples of generating images, texts, and other objects using variational autoencoders (VAE), generative adversarial networks (GANs), autoregressive models, normalizing flows, and other approaches. The assignments in the seminars are motivated by well-known applications of generative models in science and industry.