The @nytimes published "What We Know So Far About
— Eric Topol (@EricTopol) November 11, 2021
Waning Vaccine Effectiveness" today
It is misleading and missing key reports from New York State, Veterans Affairs, Puerto Rico, Israel, Qatar, the UK, and several othershttps://t.co/ST758q2d17
Are Transformers More Robust Than CNNs?
— AK (@ak92501) November 11, 2021
abs: https://t.co/UIPYvRPTrk pic.twitter.com/M3KojPHARj
Data Augmentation Can Improve Robustness
— AK (@ak92501) November 10, 2021
abs: https://t.co/9Tt4vZUcy3
github: https://t.co/VwXyAQWPeo
against ℓ∞ norm-bounded perturbations of size ϵ=8/255, model reaches 60.07% robust accuracy without using any external data pic.twitter.com/S6gMbh7WZh
How much women and men work https://t.co/PZwew8EyQq pic.twitter.com/vzlhhRJceH
— Nathan Yau (@flowingdata) November 9, 2021
NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
— AK (@ak92501) November 9, 2021
abs: https://t.co/DqwSqfuvgn pic.twitter.com/6lCs6HmLKh
Machine learning is the science of figuring out how to organize information. Information cartography, if you will
— François Chollet (@fchollet) November 7, 2021
.@Gradio Demo for AnimeGANv2 Face Portrait v2 now on @huggingface Spaces
— AK (@ak92501) November 6, 2021
demo: https://t.co/ElxylWJGwj
github: https://t.co/w7qvAwmS3m pic.twitter.com/jjnJN0ZlQf
The Deep Learning Devil is in the Details. I love this work from @IrwanBello and collaborators in which they show how training "tricks" improve ~3% absolute accuracy on ImageNet, progress equivalent to years of developments and research!
— Oriol Vinyals (@OriolVinyalsML) November 5, 2021
Paper: https://t.co/oA6MDfq1XB pic.twitter.com/auvM5yrt01
Thanks to all young Belgian PhD students who just attended my #TRAIL doctoral lecture on Deep Latent Variable Models! Slides and notes are available at https://t.co/vkGYuvqU0A @UniversiteLiege pic.twitter.com/YGCLae5iqv
— Gilles Louppe (@glouppe) November 5, 2021
The thing I’m stuck on about Zillow Data Science Discourse is the data scientists’ models could have been far more accurate as humans at predicting housing prices and still have gotten this outcome.
— Jacqueline Nolis (@skyetetra) November 5, 2021
AI ethics shopping: firms choose set of principles that justify their current behavior
— Rachel Thomas (@math_rachel) November 4, 2021
ethics washing: PR campaigns
ethics lobbying: weaken legal norms by proposing voluntary frameworks instead
ethics dumping: go to countries with weaker legal normshttps://t.co/r6vFascVkb pic.twitter.com/R3WtqaxW1X
Today on the AI2 Blog: An overview of our model Delphi as a nascent step toward machine ethics, a look into the stress testing of this research prototype, the lessons learned, and reflection on why working on imperfect solutions is better than inaction:https://t.co/ObjUwdVD5N
— Allen Institute for AI (@allen_ai) November 4, 2021
