To learn faster, dropping what is slowing you down can work wonders.
— Radek Osmulski (@radekosmulski) January 10, 2021
Great insights by @bhutanisanyam1 👉https://t.co/nPmHpB8cLY
To learn faster, dropping what is slowing you down can work wonders.
— Radek Osmulski (@radekosmulski) January 10, 2021
Great insights by @bhutanisanyam1 👉https://t.co/nPmHpB8cLY
99.98% of Americans would be correctly re-identified in any dataset using 15 demographic attributeshttps://t.co/mbwbtrZAfQ @cynddl @yvesalexandre h/t @snowjake pic.twitter.com/Xt02U7w8zw
— Rachel Thomas (@math_rachel) January 10, 2021
Stanford CS224N Natural Language Processing with Deep Learning is gearing up for its 2021 edition—starting Tue Jan 12, 4:30 Pacific for enrolled students. New lectures—transformers, LMs & KBs, new assignments—transformers, Choctaw NMT. #NLProc https://t.co/UmvB7oPVWS pic.twitter.com/tbU4I2hAzE
— Stanford NLP Group (@stanfordnlp) January 10, 2021
Offline model-based RL for goal reaching: learn a distance "Q-like" function from offline data, and a video prediction model, then use them to accomplish visually indicated goals.
— Sergey Levine (@svlevine) January 10, 2021
w/ Stephen Tian et al.https://t.co/pmXL8fGHXvhttps://t.co/x9XXI7PN06
🧵> pic.twitter.com/G3t23nBWXo
"people often resist changing their beliefs when directly challenged, especially when these beliefs are central to their identity... exposure to counterevidence may even increase a person’s confidence that their cherished beliefs are true"https://t.co/jKqFp7i3tj
— Jeremy Howard (@jeremyphoward) January 9, 2021
The simplest way to make a great software tool is to build what you want to use. The best tools are built by their own users.
— François Chollet (@fchollet) January 9, 2021
Here's a boatload of model implementations for Deep Learning on Graphs https://t.co/KZVJ6wz76A @GraphDeep https://t.co/Ne2v3rNguI
— Alex Smola (@smolix) January 8, 2021
I'm starting to prepare for the release of rvest 1.0.0. It includes big improvements to text and table extraction, and a bunch of minor API improvements. If you're an rvest user, please try out the dev version and let me know how it goes: https://t.co/qgrtknYsIK #rstats
— Hadley Wickham (@hadleywickham) January 7, 2021
Neural networks still surprise me as rich information retrieval systems. The generalization and "creativity" exhibited by @OpenAI's DALL·E is amazing! Good luck finding these images in the training distribution (see thread). pic.twitter.com/twQRunj8Rz
— Oriol Vinyals (@OriolVinyalsML) January 7, 2021
NEW: a common response to reports of hospitals struggling this winter is "it’s no different to a bad flu season!"
— John Burn-Murdoch (@jburnmurdoch) January 7, 2021
I’ve tracked down historical data on flu ICU admissions, including winter 2017-18, a record high.
Here’s how England’s Covid winter compares to a bad flu season 📹 pic.twitter.com/tsExrDZM31
IIUC this "new technique" from Facebook is actually just a slight repackaging of bits of @wightmanr's brilliant timm library.
— Jeremy Howard (@jeremyphoward) January 6, 2021
Great they wrote a paper that documented how well it works, but they should at *minimum* have cited timm, and really should have made him senior author https://t.co/53hVEjGRlG
New attention chapter in our "Dive into Deep Learning" interactive textbook (https://t.co/V7ZyrjS0hY)! Amazing effort by my collaborator @astonzhangAZ & friends. Available in @PyTorch & @ApacheMXNet. *Free* via Jupyter, HTML, PDF, & more. Thanks @AmazonScience for supporting us! https://t.co/haMhC2uJ9L
— Zachary Lipton (@zacharylipton) January 6, 2021