We make all our work publicly available so that researchers and journalists can do their best work every day.
— Our World in Data (@OurWorldInData) September 30, 2021
→ https://t.co/qdK1aoGr9U
We bring together the COVID data from around the world every day. Thousands of articles get written based on our team's daily work. pic.twitter.com/OSxY8mzb3Y
Towards Flexible Blind JPEG Artifacts Removal
— AK (@ak92501) September 30, 2021
pdf: https://t.co/9c8iaGvfpP
abs: https://t.co/oquGUTolKx
github: https://t.co/lVrbwl2dCp pic.twitter.com/ViZL23bPDa
Common error in both beginner machine learning and epidemiology:
— Jeremy Howard (@jeremyphoward) September 29, 2021
A 98% accurate model is not nearly as good as a 99% accurate one. The latter makes *half* the number of mistakes!
A 80% vaxxed population is not nearly as good as 90% vaxxed. The latter has *half* the # vulnerable
Unsolved Problems in ML Safety
— AK (@ak92501) September 29, 2021
pdf: https://t.co/aZjdACwbJY
abs: https://t.co/Fu2F70Koga pic.twitter.com/OwMjKlTpqv
Here it is! 🔥
— Matt Turck (@mattturck) September 28, 2021
After 100’s of hours of research and writing, excited to release the 2021 ***MAD*** landscape (Machine learning, Artificial Intelligence and Data) - with my colleague @john_d_wu
A crazy, intense, and fun year in the ecosystem
👇👇👇https://t.co/NQDQfaFUk7
Microsoft Turing Universal Language Representation model, T-ULRv5, has topped the XTREME leaderboard for evaluating cross-lingual generalization. Learn how recent advances enable T-ULRv5 to not only excel beyond previous models, but also train 100x faster: https://t.co/gX4ooVYGFX
— Microsoft Research (@MSFTResearch) September 28, 2021
Merlion - A Machine Learning Framework for Time Series Intelligence. https://t.co/j6vYdpg3xZ #Python #MachineLearning pic.twitter.com/gw9ng0yiCm
— Python Weekly (@PythonWeekly) September 28, 2021
Looking for ways to spruce up my decision tree lecture this week & stumbled upon the dtreeviz library compatible with scikit-learn: https://t.co/lxeFfx9pUa. Not sure if I love the pie charts, but the histograms plus split indicator are kind of nice. Also nice viz for regr trees pic.twitter.com/QUgIP70uMr
— Sebastian Raschka (@rasbt) September 28, 2021
FewNLU: Benchmarking State-of-the-Art Methods
— AK (@ak92501) September 28, 2021
for Few-Shot Natural Language Understanding
pdf: https://t.co/IhdNEnGWo8
abs: https://t.co/YO2hqCTWnk pic.twitter.com/eF7icGRVbA
Ready for a new profile pic? Meet Google Illustrations: a collection of customizable designs to help you create a profile image to represent yourself across most Google products. https://t.co/iJ26HeUCuh
— Boo-gle 👻 (@Google) September 27, 2021
"torch.manual seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision" https://t.co/LoQhOzpbVw. Results are actually not as bad as the title makes it seem. But yeah, reporting std dev or CIs should be(come) the default. pic.twitter.com/K2JElhgwCs
— Sebastian Raschka (@rasbt) September 27, 2021
Today I’m open sourcing my code for working with Twitter data
— Ryan J. Gallagher (on the job market!) (@ryanjgallag) September 27, 2021
It's designed to make advanced studies of social media easier by coordinating multiple API queries (stream, search, convos, quotes, user timelines) and organizing them using PostgreSQLhttps://t.co/2yYhfr612v
1/
