🔥We're launching the new https://t.co/FfMSiFcO73 and it's incredible
— Hugging Face (@huggingface) January 21, 2021
🚀Play live with +10 billion parameters models, deploy them instantly in production with our hosted API, join the 500 organizations using our hub to host/share models & datasets
And one more thing... 👇 pic.twitter.com/hTI1h5wNZI
It's crazy what developers can create with TensorFlow.js nowadays 😯 https://t.co/waOZDhrG9x
— François Chollet (@fchollet) January 21, 2021
I have no idea how @wjb_mattingly finds time to produce so much content, but this YouTube channel is a real treasure trove of NLP, ML, Python and @spacy_io tutorials, for Digital Humanities & beyond, from hands-on applied NER to analyzing Latin 🤓
— Ines Montani 〰️ (@_inesmontani) January 21, 2021
📺 https://t.co/8aKFe8HtNr pic.twitter.com/jL3JFHzvj3
1/2
— Judea Pearl (@yudapearl) January 20, 2021
"What are the most important statistical ideas of the past 50 years?"
A new paper by Gelman and Vehtari lists "counterfactual causal inference" as #1.https://t.co/gCL1MsGXo2
This is in stark contrast to Stigler (2016) "The seven pillars of
The fiscal policies that started with Reagan's tax cut on high incomes is what caused the blaring inequalities we see today in America (not in Europe).
— Yann LeCun (@ylecun) January 19, 2021
Want a root cause for Trump's election?
That's it.
Here is another graph for @WardQNormal (from @erikbryn & @amcafee ): https://t.co/8tYziCAbSC pic.twitter.com/f1qvrAYJr7
New code walkthrough on https://t.co/m6mT8SrKDD: the Vision Transformer model. Perform image classification *without convolutions* by applying a Transformer to vector encodings of image patches. Created by Khalid Salama.https://t.co/EanhDyZpa5
— François Chollet (@fchollet) January 19, 2021
Small Docker Images with Condahttps://t.co/Cmp2WSQYuW
— Matthew Rocklin (@mrocklin) January 19, 2021
This small blogpost from @jcristharif is old, but keeps coming up at work. I thought I'd retweet it out here for others.
#PyTorch implementation and pretrained models for
— Alexandr Kalinin (@alxndrkalinin) January 19, 2021
RepVGG: Making VGG-style ConvNets Great Againhttps://t.co/F4TnXuXr1e
- multi-branch topology at training
- simple 3x3 convs & ReLU at inference
- >80% top-1 accuracy on ImageNet
- 83% faster than ResNet-50 on NVIDIA 1080Ti pic.twitter.com/hwN60o0T78
ML and NLP Research Highlights of 2020
— Sebastian Ruder (@seb_ruder) January 19, 2021
It's been inspiring to look back on all the exciting advances that happened despite such a tumultuous year. Here's a selection of my highlights. https://t.co/yxzZCyap3v
Since @asaf_amr defended his masters yesterday, we decided its a good time to arxiv this ICLR 2020 reject.
— (((ل()(ل() 'yoav)))) (@yoavgo) January 19, 2021
It presents a *simple* constructive proof of the benefit of depth in neural nets, which, unlike other similar works, can be grasped by undergrads.https://t.co/CD7WNT79h6 pic.twitter.com/P8WuEI2kG6
This is a great blog post series by @HeyChelseaTroy on technical debt & how to avoid it 💰👇
— Ines Montani 〰️ (@_inesmontani) January 19, 2021
Featuring: how we keep maintenance load below average for @spacy_io and @explosion_ai, plus some great points on what companies can learn from open source!
Link: https://t.co/4GaRU1s4ZM https://t.co/OWPceyOfmf pic.twitter.com/FCF0L6MEYz
string.replace("sexual", "political")
— Casey Fiesler, PhD, JD, geekD (@cfiesler) January 18, 2021
Not that I was *surprised* to see this study about predicting "political orientation," but since I've been talking about the "gaydar" (sigh) algorithm from the same researcher for a while now, here's some reflection.https://t.co/gqfjUu9SuV
