Riccardo Mereu

[Vivek Galatage @vivekgalatage]

Interesting GPU performance insights by Kostas Anagnostou.

https://t.co/cemTws0pac

[Eric Zhang @ekzhang1]

For the next couple weeks at NY systems reading group, we’ll be writing some GPU kernels

This was much requested, and I think now that there’s some excellent, well-written content online about CuTe DSL, makes sense to learn!

(CUDA is too hard / arcane, CuTe DSL is just low-level enough to be interesting to systems folks looking for a new challenge perhaps. Plus it might be useful to learn it for work.)

I was trying to figure out how we give people a quick trial of Hopper/Blackwell GPUs and realized I already made a free product for this at my last job lol, and it’s on-demand + collaborative. So we’ll use Notebooks.

https://t.co/ArFSF8ESxA

[Edward Z. Yang @ezyang]

Without further ado, The Parallelism Mesh Zoo

[Riccardo Mereu @rmwu36]

@francoisfleuret @edchangy

[Peyman Milanfar @docmilanfar]

Sad to hear of the passing of legend Prof. CR Rao.

A towering figure in statistics, he's known for many seminal contributions, including the Cramér–Rao bound, and Rao–Blackwell theorem.

His legacy lives on. May his memory be a blessing.

[The Cultural Tutor @culturaltutor]

Want to know what the apocalypse will be like?

Look no further than the terrifying art of John Martin, a long forgotten 19th century painter you've probably never heard of...

[Rodney Brooks @rodneyabrooks]

1/ Mon Sept 26, 1977, 45 years ago today, I rode my bicycle up Page Mill Rd in Palo Alto, under 280, right on Arastradero, then up a driveway to a delapidated semi-circular wooden building. I walked through the front door at one end and entered the future. I have never left.

[Awni Hannun @awnihannun]

Read a bit about Grokking recently. Here's some learnings:

"Grokking" is a curious neural net behavior observed ~1 year ago (https://t.co/qH63ZOEOy0).

Continue optimizing a model long after perfect training accuracy and it suddenly generalizes.

Figure:

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Deep Visual Geo-localization Benchmark

@gabriberton R. Mereu, G. Trivigno, C. Masone, G. Csurka, @SattlerTorsten @bcaputo_iit

tl;dr: modular image retrieval benchmark on visloc datasets. Study: backbones, mining, ANN, aug, data.
https://t.co/imSTJ1iGuD
https://t.co/GPhdaaTxH2

[Riccardo Mereu @rmwu36]

@lucacarlone1 I’m interested! Thank you for doing this!

[Sven @SvenSchnieders]

@lexfridman Books over news.

[Google DeepMind @GoogleDeepMind]

We’re back with more #AtHomeWithAI researcher recommendations. Next up is research scientist @csilviavr with suggestions for resources to learn about causal inference! (1/5)

[François Chollet @fchollet]

The speed at which I accumulate open tabs in Chrome is alarming. I have to declare tab bankruptcy every couple days

[George Mack @george__mack]

THREAD: 15 of the most useful razors and rules I've found.

Rules of thumb that simplify decisions.

[Andrej Karpathy @karpathy]

How to become expert at thing:
1 iteratively take on concrete projects and accomplish them depth wise, learning “on demand” (ie don’t learn bottom up breadth wise)
2 teach/summarize everything you learn in your own words
3 only compare yourself to younger you, never to others

[Prof. Feynman @ProfFeynman]

You cannot get educated by this self-propagating system in which people study to pass exams, and teach others to pass exams, but nobody knows anything.

You learn something by doing it yourself, by asking questions, by thinking, and by experimenting. 🧠