Ashwin De Silva

PhD student @JohnsHopkins, alum @ENTC_UoM, all things ML (esp. generalization under distribution shifts) 🇱🇰 🇦🇺 🇺🇸

[Ashwin De Silva @AshwindeSilva1]

First stride of my PhD will appear at #ICML2023 @icmlconf 💫

📜 https://t.co/EIqZmJmvnO

w/ @RahulRam3sh Carey E. Priebe @pratikac @neuro_data

1/3

[Kording Lab 🦖 @KordingLab]

While much of machine learning is retrospective (learn the past distribution) learning in biology is prospective (learn for the future) - here we discuss some implications for neuroscience (with Tim Verstynen, @jovo, Pratik Chaudhari): https://t.co/gEKuO1JT9c

[Blake Richards @tyrell_turing]

4/ Retrospective ➡️ Prospective

Standard RL is retrospective ("do more of what worked before"). But social settings are non-stationary because other agents are also learning.

This requires prospective learning – predicting the future to anticipate how other agents will adapt.

[Alfredo Canziani @alfcnz]

Optimization Algorithm Design via Electric Circuits @StephenPBoyd1

[Dumitru Erhan @doomie]

#NeurIPS2024 parties be like this;

[Peyman Milanfar @docmilanfar]

Are you preparing for a (Research Scientist) job talk in industry? What generally works well is to give your presentation the following structure:

First, a short snippet of your overall set of technical accomplishments. For instance, you might spend the first 15 minutes giving short overviews of a few of your works/papers - it's also very good to draw a theme across them if there is one.

Second, you can spend the next 20-25 minutes doing a deep dive on just one of them - say, the one you're most proud of, or the one that matches the hiring team's interests best.

And finally, use the last 5-10 minutes to summarize and talk about what you think are important new directions to pursue in research and how these could have impact for the team and the products of the company.

In my experience, it's hard to give a bad talk that's structured like this. And as a bonus, the form is flexible enough to adapt to different audiences.

[Felix Hill @FelixHill84]

Do you work in AI?

Do you find things uniquely stressful right now, like never before?

Haver you ever suffered from a mental illness?

Read my personal experience of those challenges here:

https://t.co/OFZmSizl6f

[The Nobel Prize @NobelPrize]

BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

[Peyman Milanfar @docmilanfar]

You should be so lucky to have people throughout your research career that you can openly bounce ideas to and from - especially if they complement your strengths in your areas of weakness - it is a rare and precious gift.

[Itai Yanai @ItaiYanai]

Doing good science is 90% finding a science buddy to constantly talk to about the project.

[Paul Middlebrooks @pgmid]

We don't get "redos" in all matters, but Jovo @neuro_data explains why he's an advocate. Oh, and we chat about prospective learning, baby fly connectomes, theoretical neuroscience, and how to be an expert meditator out of the gate...

https://t.co/KZR6AoxGtX

[Ashwin De Silva @AshwindeSilva1]

@ramith__ @ChamiraEduss @prathapakd @rangarodrigo @nawodya @sokrypton All the best @ramith__! Keep doing great stuff 💯

[Yuri Sagalov @yuris]

Me: “lol they finally brought a calculator to the iPad”

Me 2 minutes later: “holy crap math notes are amazing”

[Ashwin De Silva @AshwindeSilva1]

Highly recommended!

[Ransalu Senanayake @Ransalu]

#PhD Positions

I am looking for #PhD students with a background in #MachineLearning, #DeepLearning, or #Robotics to start in Fall'24. DM me with a link to your CV.

@phd_position @AcademicChatter #AcademicChatter #AcademicTwitter
@PostdocVoice #PostdocVoice
@PhDVoice #PhDVoice

[François Chollet @fchollet]

While intelligence *leverages* compression in important ways in representation learning, intelligence and compression are by nature opposite in key aspects.

Because intelligence is all about *generalization to future data (out of distribution)* while compression is all about *efficiently fitting the distribution of past data*. If you're optimal at the latter, you're terrible at the former.

If you were an optimal compression algorithm, the behavior policy you would develop during the first 10 years of your life (maximizing your extrinsic rewards such as candy intake, while forgetting all information that appears useless as per past rewards) would be entirely inadequate to handle the next 10.

[Pablo Samuel Castro @pcastr]

One thing I've learned about ML researchers on this platform is that they're not just ML experts, they're also experts on cognitive science, geopolitical conflicts, how to run companies, and lots more things to come!

[Kording Lab 🦖 @KordingLab]

This paper set the stage for much of machine learning according to Jovo. could someone translate it to Engish or share a translation?

[Ashwin De Silva @AshwindeSilva1]

👀

[Gavin Crooks @gavincrooks]

Today: UC Berkeley Physics Colloquium with Gavin Crooks, "Thermodynamic Linear Algebra", Lecture Hall #1, Physics North, 4:14-5:15pm https://t.co/5jWAmwMCWF https://t.co/C7ekCzpPPn

[Andrew Shtulman @andrewshtulman]

A colleague of mine just accepted a tenure-track job that includes a burial plot in the College's cemetery. What a perk!