Lecture: 2.01.5400 Deep Unsupervised Learning - Details

Lecture: 2.01.5400 Deep Unsupervised Learning - Details

You are not logged into Stud.IP.

General information

Course name Lecture: 2.01.5400 Deep Unsupervised Learning
Subtitle inf5400
Course number 2.01.5400
Semester WiSe24/25
Current number of participants 10
expected number of participants 20
Home institute Department of Computing Science
participating institutes Institute of Physics
Courses type Lecture in category Teaching
Next date Friday, 08.11.2024 14:00 - 16:00, Room: V03 2-A208
Type/Form V+Ü
Lehrsprache deutsch und englisch

Rooms and times

V03 2-A208
Thursday: 08:00 - 10:00, weekly (13x)
Friday: 14:00 - 16:00, weekly (14x)

Comment/Description

This lecture encompasses two primary subjects: self-supervised learning and modern generative models. In the first part, we will examine the fundamental design principles (contrastive versus non-contrastive) underlying self-supervised learning algorithms. In the second part, we will explore applications of these principles to specific data modalities such as computer vision, natural language processing (including an extensive coverage of large language models) and audio/time series. Finally, the third part will focus on generative models, where we will cover a wide array of models, ranging from autoregressive models, variational autoencoders, and normalizing flows, to generative adversarial networks and (latent) diffusion models.