
Mathematics and beauty. Chaotic systems. Strange attractors. More info: https://t.co/cqSv9aaB5s

C.S. PhD, Lead R&D @ Disaitek, AI innovator @ Intel.

Mathematics and beauty. Chaotic systems. Strange attractors. More info: https://t.co/cqSv9aaB5s

JupyterLab 3.0 is released! - visual debugger - support for multiple display languages - table of content for notebooks - improved extension system. Check out the announcement blog post. blog.jupyter.org/jupyterlab-…

This is probably the most humbling & awe-inspiring image of the #universe I know. It's an infrared image by the #spitzer #space #telescope, as wide as the full moon. The dots aren't stars. They're galaxies. Each dot is 100s of Billions of stars.(1/n) @Todd_Scheve #astronomy


"A vegan diet is probably the single biggest way to reduce your impact on planet Earth, not just greenhouse gases, but global acidification, eutrophication, land use and water use,..., far bigger than cutting down on your flights or buying an electric car" theguardian.com/environment/…

We wrote a longer version of the @huggingface🤗transformers paper (EMNLP demos). It goes through the library and model hub. Lot has happened in the last 9 months! Paper: arxiv.org/abs/1910.03771 Consider citing (not linking) in your next paper: github.com/huggingface/trans…

I'm beyond stoked to launch the v2 of the @huggingface model hub today 🔥 Each of our 2,000 models now has an inference widget that lets you try it (text-classification, token-classification, translation, etc.) directly from the model page. It's all powered by the community 💖

A surprising result: We found that smooth activation functions are better than ReLU for adversarial training and can lead to substantial improvements in adversarial robustness. arxiv.org/abs/2006.14536

Check out our new work "Labelling unlabelled videos from scratch with multi-modal self-supervision" by @y_m_asano @mandelapatrick_ @chrirupp and Andrea Vedaldi in colab with @facebookai! See below for our automatically discovered clusters on VGG-Sound! robots.ox.ac.uk/~vgg/researc…

Unsupervised Translation of Programming Languages. Feed a model with Python, C++, and Java source code from GitHub, and it automatically learns to translate between the 3 languages in a fully unsupervised way. arxiv.org/pdf/2006.03511.pdf with @MaLachaux @b_roziere @LowikChanussot

Long-range sequence modeling meets 🤗 transformers! We are happy to officially release Reformer, a transformer that can process sequences as long as 500.000 tokens from @GoogleAI. Thanks a million, Nikita Kitaev and @lukaszkaiser! Try it out here: colab.research.google.com/dr…

My face is embedded in this image. When it is blurred, e.g. seen from a distant or without a pair of glasses, my face is discernible. I have learned by myself how to make this type of illusion, but I do not know whom I should cite for this effect. Does anyone have information?

a method of drawing infinitely many touching circles

RIP John Conway xkcd.com/2293/ m.xkcd.com/2293/

T5 is now officially included in 🤗Transformers v2.7.0 thanks to our joint work with @colinraffel & @PatrickPlaten A powerful encoder-decoder by @GoogleAI which natively handles many NLP tasks as text-to-text tasks Just ask it to "Translate" or "Summarize" and enjoy the result!

🔥 Google AI weights, directly inside @huggingface transformers 🔥 x.com/huggingface/status/123… huggingface.co/google
Efficient mini-BERT models from Google Research, now available at huggingface.co/google thanks to @iuliaturc / @GoogleAI ! 24 sizes pre-trained directly with MLM loss and are competitive to more elaborate pre-training strategies involving distillation (arxiv.org/abs/1908.08962).