Event
The dates and events shown here are dynamically displayed from Stud.IP.
Therefore, if you have any questions, please contact the person listed under the item Lehrende/DozentIn (Lecturers) directly.
Event
Semester:
Winter term
2024
2.01.5400 Deep Unsupervised Learning -
Event date(s) | room
- Donnerstag, 17.10.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 18.10.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 24.10.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 25.10.2024 14:00 - 16:00 | V03 2-A208
- Freitag, 1.11.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 7.11.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 8.11.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 14.11.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 15.11.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 21.11.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 22.11.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 28.11.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 29.11.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 5.12.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 6.12.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 12.12.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 13.12.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 19.12.2024 8:00 - 10:00 | V03 2-A208
- Freitag, 20.12.2024 14:00 - 16:00 | V03 2-A208
- Donnerstag, 9.1.2025 8:00 - 10:00 | V03 2-A208
- Freitag, 10.1.2025 14:00 - 16:00 | V03 2-A208
- Donnerstag, 16.1.2025 8:00 - 10:00 | V03 2-A208
- Freitag, 17.1.2025 14:00 - 16:00 | V03 2-A208
- Donnerstag, 23.1.2025 8:00 - 10:00 | V03 2-A208
- Freitag, 24.1.2025 14:00 - 16:00 | V03 2-A208
- Donnerstag, 30.1.2025 8:00 - 10:00 | V03 2-A208
- Freitag, 31.1.2025 14:00 - 16:00 | V03 2-A208
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.
Lecturers
SWS
4
Lehrsprache
deutsch und englisch