Recorded lectures: https://uni-bielefeld.sciebo.de/s/IJQsTwNzRf9hYJM
The lecture starts on Mondays at 8:30am online (see Zoom link below).
Most of the lectures will be available in video recordings.
Tutorials will begin in the first week of November.
Topics:
CLIP: Connecting text and images https://openai.com/research/clip
CLIP Interrogator https://huggingface.co/spaces/pharmapsychotic/CLIP-Interrogator https://huggingface.co/spaces/fffiloni/CLIP-Interrogator-2
SAM: Segment Anything Model https://segment-anything.com
Grounded SAM https://github.com/IDEA-Research/Grounded-Segment-Anything
ChatGPT https://chat.openai.com
GPT4 https://openai.com/gpt-4
VPT: Learning to play Minecraft with Video PreTraining https://openai.com/research/vpt
Stable Diffusion https://stability.ai/blog/stable-diffusion-public-release
ControlNet https://github.com/lllyasviel/ControlNet
Tracking Everything Everywhere All at Once https://omnimotion.github.io
StyleGAN https://nvlabs.github.io/stylegan3/
Zoom: https://uni-bielefeld.zoom.us/j/92186588995?pwd=UGNXdm5XRVNwMFgxdXdWV25mS2tzUT09
Meeting ID: 921 8658 8995
Passcode: 123123
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-VML Vertiefung Maschinelles Lernen | Vertiefung Maschinelles Lernen | Ungraded examination
Graded examination |
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.