Deep learning researcher.
Joined May 2020
- Tweets 8
- Following 38
- Followers 11
- Likes 267
Photos and videos
4 Jan 2021
Happy New Year! In 2020, I trained 417 models over 1,851 hours, with 1,140 hours of GPU training time. Get insights on your model training with @wandb! #myyearwrapped
3
2 Jun 2020
Vielen Dank für die Unterstützung Monika! War extrem wertvoll bei deinem Kurs mitzumachen zu dürfen :) Nur zu empfehlen: #3WeeksofTwitt
18 May 2020
Cool music generated with VQ-VAE models @michaelhgraber & @3WeeksofTwitt
Introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We're releasing a tool for everyone to explore the generated samples, as well as the model and code: openai.com/blog/jukebox/
1
1
14 May 2020
Impressive image generation quality with quantization.
4 Jun 2019
VQVAE-2 finally out!
Powerful autoregressive models in a hierarchical compressed latent space. No modes were collapsed in the creation of these samples ;)
Arixv: arxiv.org/abs/1906.00446
With @catamorphist and @vinyals
More samples and details 👇 [thread]
14 May 2020
Very interesting and useful to reduce the number of labels required.
9 Dec 2019
Unsupervised pre-training now outperforms supervised learning on ImageNet for any data regime (see figure) and also for transfer learning to Pascal VOC object detection
arxiv.org/abs/1905.09272v2
Marco Willi retweeted
9 Dec 2019
Unsupervised pre-training now outperforms supervised learning on ImageNet for any data regime (see figure) and also for transfer learning to Pascal VOC object detection
arxiv.org/abs/1905.09272v2
4
191
709
14 May 2020
Interesting adversarial attack by employing "off-distribution" actions