Andrew Delong

Making ML work better. Genomics, vision, optimization. Assistant Prof at Concordia University. {{ Looking for great students! }}

[John Carmack @ID_AA_Carmack]

I resigned from Meta, and my internal post got leaked to the press, resulting in some fragmented quotes. Here is the full thing: https://t.co/iUcr8TYMLD

[James Zou @james_y_zou]

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!

[James X. Li @VisuMap]

@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.

[Abraar Karan @AbraarKaran]

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.

https://t.co/r1KfeKHW5J

[Eric Topol @EricTopol]

The 5-minute, low-cost virus test using #CRISPR, a mobile phone, without fancy equipment, for point-of-care
https://t.co/1m4292jhlk @RobertFService @ScienceMagazine @NewsfromScience
https://t.co/oXBGoVDqiS @TheOttLab @GladstoneInst @doudna_lab

[Hossein Mobahi @TheGradient]

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://t.co/570qXFmlGj w/@farajtabar P.Bartlett

[Steven Pinker @sapinker]

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. https://t.co/9kXzHhsKOO

[Sara Mostafavi @sara_mostafavi]

#MLCB2020 is happening! A fully independent virtual conference this year, Nov 23-24. Checkout the amazing line up of keynote speakers: https://t.co/LYuJI7fUX2
Abstract deadline: Sept 30th. @anshulkundaje @suinleelab @james_y_zou @david_a_knowles @QuonBio

[Jo(sephine) Lukito @JosephineLukito]

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 @adelong]

@mfg81 Roger that. I sent Dan my new number 😬

[Andrew Delong @adelong]

This is a great idea: construct "separate embedding spaces, each invariant to all but one augmentation." https://t.co/c1LdI7khKa

[Mohammed AlQuraishi @MoAlQuraishi]

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 https://t.co/x3SHeZPFiD. 1/2

[Georg Seelig @seeliglab]

Interested in using deep learning for designing proteins or cis-regulatory sequences? Try out this new (and fast) method by the very talented @jjohli: https://t.co/1wfb912Bgz

[Eric Topol @EricTopol]

What is your micromort risk of #COVID19?
https://t.co/y6EviksU5b
1 micromort =one-in-a-million chance of dying
by @DRobertsNYC

[Scott Gottlieb, MD 🇺🇸 @ScottGottliebMD]

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: https://t.co/6MYgYDvkHZ

Or on the Munk Debates website: https://t.co/uzlJlGoaUL

[John Carreyrou @JohnCarreyrou]

A smart take on virus testing by one of my Theranos sources. You may have heard of him: his first name is Tyler... https://t.co/LYFdpjHpBH

[Geoffrey Hinton @geoffreyhinton]

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.

[Ben Cowling @bencowling88]

(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 https://t.co/nXJOKLVTvk

[Andrew Delong @adelong]

https://t.co/0ULTDNJQIF

[Nicholas A. Christakis @NAChristakis]

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. https://t.co/6mkH9AvtkL via @marcelsalathe #quarantineloophole 30/