Andrew Delong retweeted
I resigned from Meta, and my internal post got leaked to the press, resulting in some fragmented quotes. Here is the full thing: facebook.com/permalink.php?s…
Andrew Delong retweeted
Super excited by this new #ICML paper: we find that many deep nets have a few (<50) "critical" neurons and we have an efficient alg to find them.
Evaluating these critical neurons enables fast model repair (e.g. reduce bias) and interpretation. Great work by @GhorbaniAmirata!
Andrew Delong retweeted
Replying to @hippopedoid @jhnhw
I occasionally encountered similar artifact with scRNA seq data. The spaghetti-loop in UMAPs changes completely when you shuffle the order of rows in the training data.
Andrew Delong retweeted
The graphics in this article are excellent— this is a huge part of communications that has been missing. If you want to understand how layered interventions reduce #covid19 spread— why masks are indispensable but not always “enough” — read this.
english.elpais.com/society/2…
Andrew Delong retweeted
The 5-minute, low-cost virus test using #CRISPR, a mobile phone, without fancy equipment, for point-of-care
sciencemag.org/news/2020/10/… @RobertFService @ScienceMagazine @NewsfromScience
medrxiv.org/content/10.1101/… @TheOttLab @GladstoneInst @doudna_lab
Andrew Delong retweeted
1/5 Self-Distillation loop (feeding predictions as new target values & retraining) improves test accuracy. But why? We show it induces a regularization that progressively limits # of basis functions used to represent the solution. https://teapawt.net/t.co/570qXFmlGj w/@farajtabar P.Bartlett
Andrew Delong retweeted
Trolley problems ("Kill 1 to save 5?") are good for clarifying moral intuitions, but my grad student Julian DeFreitas argues they're irrelevant to designing driverless cars, which should kill no one. gsas.harvard.edu/news/storie…
Andrew Delong retweeted
#MLCB2020 is happening! A fully independent virtual conference this year, Nov 23-24. Checkout the amazing line up of keynote speakers: mlcb.org/
Abstract deadline: Sept 30th. @anshulkundaje @suinleelab @james_y_zou @david_a_knowles @QuonBio
Andrew Delong retweeted
My biggest regret as a 1st year grad student was pretending to say I knew X when I didn't really. Learning to say "No, tell me about X" became a gateway for (1) learning stuff, (2) getting to know a person, and (3) learning how to say no in other areas of my life.
Andrew Delong retweeted
Some news! After many lovely years at @harvardmed I'm moving to @Columbia fall 2020 to start a new lab as an Assistant Professor in Systems Biology and the Program for Mathematical Genomics--and I'm recruiting students and postdocs! Email/DM me or see aqlab.io. 1/2
Andrew Delong retweeted
Interested in using deep learning for designing proteins or cis-regulatory sequences? Try out this new (and fast) method by the very talented @jjohli: arxiv.org/abs/2005.11275
Andrew Delong retweeted
What is your micromort risk of #COVID19?
nytimes.com/2020/05/22/well/…
1 micromort =one-in-a-million chance of dying
by @DRobertsNYC
Andrew Delong retweeted
Join me at 8PM ET tonight for a live @munkdebate Q&A, where we'll discuss #covid19 and the post-pandemic world.
Tune in on Facebook: facebook.com/munkdebates
Or on the Munk Debates website: munkdebates.com/dialogues/sc…
Andrew Delong retweeted
A smart take on virus testing by one of my Theranos sources. You may have heard of him: his first name is Tyler... link.medium.com/sfw4ez9x95
Andrew Delong retweeted
This is a really neat way of using neural networks to get rid of polygonal meshes. The interaction of computer graphics with neural networks is really exciting.
NASA: Neural Articulated Shape Approximation
Representing characters and deformable shapes without polygonal meshes for 3D perception, games, ...
arxiv.org/pdf/1912.03207.pdf
Andrew Delong retweeted
(1/2) New study just out, face masks effective for source control against influenza and seasonal coronaviruses, even reducing virus detection in aerosols in patients with coronavirus infections. 5 years of hard work to generate the data nature.com/articles/s41591-0…
Andrew Delong retweeted
More evidence of pre-symptomatic transmission of COVID19, which I think we must now regard as the reality we are facing. This paper estimates that 44% of transmission could occur 2-3 days before first symptoms. medrxiv.org/content/10.1101/… via @marcelsalathe #quarantineloophole 30/
Andrew Delong retweeted
Let’s talk about what happens if you get COVID19 and recover. Are you immune to the disease? How long does the immunity last? And what does that mean for your life and for the public health and economy of our society? 1/
Andrew Delong retweeted
You are young and still wanna go out to bars cause you think, meh, I won't get this virus or if I do, it won't hit me hard. Read this:
Andrew Delong retweeted
Saw this interesting project on r/ML that seems to be highly unconventional and non-mainstream. There are many independent researchers who have their own theories of how AI should work, but they have a GitHub repo, papers, and decent RL benchmark results.
github.com/Guillemdb/Fractal…




























