Neerav

research scientist @quantco | ML for healthcare

[Timur Garipov @tim_garipov]

Yesterday, I successfully defended my PhD thesis "Guiding Deep Probabilistic Models".

I have been so lucky to be advised by Tommi Jaakkola and to have the support of my thesis committee members: @samikaski and @phillip_isola.

Defense slides: https://t.co/u0r6DakdUl

[Neerav @nirav_karani]

@RisingSayak Very true. Good news though is that the number of vegan places is increasing fairly rapidly in western Europe in recent years. https://t.co/1xGf5eT6OM

[Neerav @nirav_karani]

Race to Nowhere.

[Gautam Kamath @thegautamkamath]

NeurIPS 2024 will have a track for papers from high schoolers.

[Neerav @nirav_karani]

The struggle is real. https://t.co/F8aSNvRdbS

[Hariri Institute for Computing, Boston University @BU_Computing]

Join us Friday 1/26 at 2pm ET for a virtual MLxMED Seminar "Expert load matters: operating networks at high accuracy and low manual effort" presented by Dr. @EnderKonukoglu @ETH_en
@kbatmang @PittTweet @UofT
Learn more: https://t.co/mnKc39n54G

[Neerav @nirav_karani]

@adad8m @michael_nielsen The story I told myself is that in 1D, we can make "spikes" with 3 ReLUs (https://t.co/jqOgQaqZlT) similar to making "bumps" with 2 step functions. Everything else should work is the same way as in @michael_nielsen's book.

[Neerav @nirav_karani]

Really happy to have stumbled upon @michael_nielsen's fantastic visual proof of the universal approximation theorem - https://t.co/4YXPj1mzlH

[Jose Dolz @josedolz_ets]

If you are looking for an exciting PhD in a dynamic and vibrant city (Montreal), drop me an email with your CV and cover letter. Two positions opened: 1) uncertainty in large-foundation models for medical image analysis and 2) few-shot continual learning in multi-modal learning.

[Neerav @nirav_karani]

Me reading a paper.

[The Figen @TheFigen_]

Awww that reaction. 😂

https://t.co/2MV6KQluS3

[Neerav @nirav_karani]

@gokstudio Are data-hungry LLMs secretly snacking on web pages?

[Neerav @nirav_karani]

@schirmermd @NIHAging @NIH Congrats, Markus!

[Michael Black @Michael_J_Black]

In the LLM-science discussion, I see a common misconception that science is a thing you do and that writing about it is separate and can be automated. I’ve written over 300 scientific papers and can assure you that science writing can’t be separated from science doing. Why? 1/18

[Neerav @nirav_karani]

@mnwsth जैन आए

[Phillip Isola @phillip_isola]

We’re releasing a new image similarity metric and dataset!

--> DreamSim: a metric which outperforms LPIPS, CLIP, and DINO on similarity and retrieval tasks
--> NIGHTS: a dataset of synthetic images with human similarity ratings

paper+code+data: https://t.co/Pu49mVj540

1/n

[Nalini Singh @nalinimsingh]

I'm presenting this Thursday at #ISMRM23!

Motion-Aware Neural Networks Improve Rigid Motion Correction Of Accelerated Segmented Multislice MRI
Oral #1371, Thursday, 06/08 16:24 - 16:32, Room 701B

Also viewable anytime as an AMPC Selection Poster in the main exhibition area.

[Meritxell Bach Cuadra @MeriBach]

📢2 PhD student positions in my group @CIBM_ch @FBM_UNIL @unil Opportunity funded to pursue impactful #machinelearning and #MRI research: domain-shifts #DL #pediatric #brain #low-field MRI quantitative mapping. #Interdisciplinary team, best project partners ever🤩! 🙏RT👇#hiring

[Andrew Gordon Wilson @andrewgwils]

Virtually every ML paper is a method comparison, where the authors almost always have a "horse in the race". This is bad for science. We need to diversify and embrace empirical studies that are not incentivized to push a particular narrative or make a specific method look good.

[Suchi Saria @suchisaria]

Excited to see @bayesianhealth on @Forbes AI 50!

It’s been quite the year in AI with 100s/1000s of new ventures focusing in the space. Great to see other amazing peers and friends also recognized!