|
Sander Dieleman
@
sedielem
London, England
|
|
Research Scientist at DeepMind. I tweet about deep learning (research + software), music, generative models, Kaggle, Lasagne (lasagne.readthedocs.org)
|
|
|
1.000
Tweetovi
|
666
Pratim
|
36.876
Osobe koje vas prate
|
| Tweetovi |
|
|
Sander Dieleman
@sedielem
|
15 h |
|
Thanks! It's the London skyline actually :)
|
||
|
||
|
|
Sander Dieleman
@sedielem
|
21. sij |
|
Deep Learning Lecture Series at UCL, starting Feb 3rd. (Free) tickets are available now. I will be talking about convolutional neural networks on Feb 17th! twitter.com/DeepMind/statu…
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Jesse Engel
@jesseengel
|
15. sij |
|
Differentiable Digital Signal Processing (DDSP)! Fusing classic interpretable DSP with neural networks.
⌨️ Blog: magenta.tensorflow.org/ddsp
🎵 Examples: g.co/magenta/ddsp-e…
⏯ Colab: g.co/magenta/ddsp-d…
💻 Code: github.com/magenta/ddsp
📝 Paper: g.co/magenta/ddsp-p…
1/ pic.twitter.com/SlxLUOUC6k
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Jeffrey De Fauw
@JeffreyDeFauw
|
1. sij |
|
Very excited to share nature.com/articles/s4158… where we show an AI system that outperforms specialists at detecting breast cancer during screening in both the UK and US. Joint work with @GoogleHealth and @CR_UK published in @Nature today! pic.twitter.com/SL6NV6KyuY
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Luba Elliott
@elluba
|
18. pro |
|
My AI art online gallery for 2019 is finally live 🎉 🎉🎉
Check out all the art, music and design projects submitted to our #NeurIPS4Creativity Workshop😍
aiartonline.com
#NeurIPS2019 #AIart #CreativeAI pic.twitter.com/OYAa1jQ1Wa
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
|
Luba Elliott
@elluba
|
14. pro |
|
Poster Session 1 happening at the #NeurIPS4Creativity Workshop until 2.30pm. Drop by for Korean abstract painting, creative GANs and generative models without data 🚀#NeurIPS2019 pic.twitter.com/ubkY1xaPzy
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Adam Roberts
@ada_rob
|
13. pro |
|
I'm so excited about the program we've put together for Saturday's #NeurIPS2019 ML for Creativity and Design Workshop 3.0.
Aside from the amazing accepted talks and posters, we have a diverse set of invited speakers I want to highlight in this thread.
neurips2019creativity.github.io
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
|
Luba Elliott
@elluba
|
10. pro |
|
Full Schedule and accepted papers for our Creativity Workshop now live on neurips2019creativity.github.io
See you on Saturday 14th Dec in West 223-224 🤖🎨
#NeurIPS2019 #neurips4creativity pic.twitter.com/Q466FFQkgz
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Aäron van den Oord
@avdnoord
|
9. pro |
|
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/1905.09272… pic.twitter.com/cciL5Db73x
|
||
|
|
||
|
|
Sander Dieleman
@sedielem
|
8. pro |
|
Heading to Vancouver for #NeurIPS2019! I'll be around all week, check out our workshop on ML for creativity and design on Saturday! neurips2019creativity.github.io
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Danilo J. Rezende
@DeepSpiker
|
6. pro |
|
Looking for something to read in your flight to #NeurIPS2019? Read about Normalizing Flows from our extensive review paper (also with new insights on how to think about and derive new flows) arxiv.org/abs/1912.02762 with @gpapamak @eric_nalisnick @DeepSpiker @balajiln @shakir_za pic.twitter.com/EWh8Aui7n0
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Utku
@utkuevci
|
26. stu |
|
End-to-end training of sparse deep neural networks with little-to-no performance loss. Check out our new paper: “Rigging the Lottery: Making All Tickets Winners” (RigL👇) !
📃 arxiv.org/abs/1911.11134
📁 github.com/google-researc…
with @Tgale96 @jacobmenick @pcastr and @erich_elsen pic.twitter.com/LmR18hK4LV
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
DeepMind
@DeepMind
|
26. stu |
|
“Fast Sparse ConvNets”, a collaboration w/ @GoogleAI [arxiv.org/abs/1911.09723], implements fast Sparse Matrix-Matrix Multiplication to replace dense 1x1 convolutions in MobileNet architectures. The sparse networks are 66% the size and 1.5-2x faster than their dense equivalents. pic.twitter.com/poDKMzfA4u
|
||
|
|
||
|
|
Sander Dieleman
@sedielem
|
21. stu |
|
😊 that's really cool to hear! @kwwillett deserves a massive amount of credit as well for setting the stage for this work. I would not have worked on this problem if it weren't for the Kaggle competition, and I wouldn't have been able to submit to MNRAS without his help!
|
||
|
|
||
|
|
Sander Dieleman
@sedielem
|
15. stu |
|
Moltes felicitats :)
|
||
|
|
||
|
|
Sander Dieleman
@sedielem
|
12. stu |
|
Congrats Colin :)
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
Jordi Pons
@jordiponsdotme
|
5. stu |
|
Here the slides of our tutorial on "Waveform-based music processing with deep learning" organised by @sedielem, Jongpil Lee and myself!
- Zenodo: zenodo.org/record/3529714…
- Google Slides: docs.google.com/presentation/d… pic.twitter.com/7yxhDOKluS
|
||
|
|
||
|
|
Sander Dieleman
@sedielem
|
4. stu |
|
Hey Vincent, the point I was trying to make is that the frequency decomposition in our ears is a result of a learning algorithm (evolution), so it's not surprising that raw waveform based discriminative models would learn to do something similar. Come find me, happy to discuss :)
|
||
|
|
||
|
|
Sander Dieleman
@sedielem
|
3. stu |
|
I'm at #ISMIR2019 until Wednesday! My first ISMIR in 5 years :) I'll be co-presenting a tutorial about raw audio music processing and generation with @jordiponsdotme and Jongpil Lee on Monday afternoon.
|
||
|
|
||
| Sander Dieleman proslijedio/la je tweet | ||
|
George Papamakarios
@gpapamak
|
30. lis |
|
My PhD thesis is now available on arXiv:
Neural Density Estimation and Likelihood-free Inference
arxiv.org/abs/1910.13233
There's a lot in it for those interested in probabilistic modelling with normalizing flows, and in likelihood-free inference using machine learning.
(cont.) twitter.com/driainmurray/s…
|
||
|
|
||