Interpretable Deep Learning for New Physics Discovery

[@MCRuCr]

A python package with a julia backend ? What a time to be alive!

[@MarkMark]

Also, I can't wait for the Elixir NX / Axon version. ; )

[@billykotsos4642]

Wow

[@frun]

Next: school homework doing itself. What a time to be alive!

[@tanchienhao]

two-minute papers? :)

[@memegazer]

@@tanchienhao "Dear Fellow Scholars, this is Two Minute Papers with Dr. Károly Zsolnai-Fehér."

[@SciFiFactory]

From now on, when I am fooling around, trying out different formulas, I will call it "manual symbolic regression". Thanks a lot! :D

[@yuyingliu5831]

This is one of the best works I have read about earlier this year, thanks for the lecture that makes it is more clear.

[@jameswalters8755]

"When one does a theoretical calculation, there are two ways of doing it. Either you can have a clear physical model in mind or you should have a rigorous mathematical basis." -Freeman Dyon recounting his meeting with Enrico Fermi.

[@G12GilbertProduction]

You got the sources of this quote?

[@jameswalters8755]

Start at 1:15 end at 1:27 on KZbin Freeman Dyson - Fermi's rejection of our work (94/157) Cheers!

[@HD-qq3bn]

very interesting work，but one thing is the efficiency of genetic algorithm, maybe the MCMC or HMC method can obtain a higher search efficiency

[@ccdavis94303]

IMO, this is a profound direction for research. Congratulations to the entire team. The improved generalization gives me chills.

[@joey199412]

One step closer to stop having neural networks be complete black boxes. Great work.

[@QSuperstar888]

Absolutely incredible lecture - continually coming back to the well on this one

[@SciFiFactory]

This is absolutely amazing! It feels like this is the biggest step (that I have seen) towards machines literally making discoveries and teaching us! And the fact that I understood most of it despite me having no experience in AI or programming makes me happy and is a giant praise to the presenter! I love it and I'll tell everyone about it! :D

[@smoothcortex]

Very interesting! I wish psychology and neuroscience applied similar models! The brain and associated behaviour would be a lot easier to organise and interpret if we had symbolic methods of representing the interactions.

[@The231998]

Wow, the world needs more videos like this

[@NoNTr1v1aL]

Absolutely amazing video!

[@gianpierocea]

Wow, super cool, very happy I stumbled upon this video. A question, at the end of this process do you just get a "point estimate" in the space of functions that have the basis you gave? If so, how difficult would it be to obtain a probabilistic generative model that gives you a "distribution" of functions? I am completely in the dark about this topic, but definitely wanting to know more. Cool stuff!

[@jedhomer4381]

Amazing stuff! Miles Cranmer is a genius!

[@ahmadhasabi4829]

Very interesting, I want to apply it in Geophysics

[@danmckstwexkrpfe]

let me know what you find!

[@476megaman]

This kid is a pure empiricist at heart.

[@omarsinno2774]

**Start of the video** Miles: if you forget everything from this, i need you to remember:... Me: oh man i hope he's not saying this cause it's boring **End of the video** Me: this man is a god

[@vahidhosseinzadeh4630]

Thank you. This is really cool. Is your package available also in Julia itself?

[@nicolasbozzo2364]

Great, will try to apply it to Economics

[@frederickmannings8700]

This will start a new field

[@nbme-answers]

2:58 for the immunologists out there, this is somatic hypermutation for expressions!

[@banghuaxu4735]

Brilliant idea!!

Hey Steve, are you saying that neural networks are models of the brain? What if that brain was Newton's brain? Congratulations, Mr. Cranmer. A major breakthrough.

[@ewal31]

I am curious how this is different or better than what was done in the AI Feynman papers

[@mortengrum1258]

Could you add a reference to the work on extracting fluid dynamics PDEs from a trained GNN that was/is co-led by Elaine Cui (Flatiron Inst)? Link to pre-prints would be fine too. Thanks!

[@WhenThoughtsConnect]

I think this is like the PCA of one subclass of a vector component like a matrix column and not the row.

[@TheStrings-83639]

Well it looks like what I did in Excel making the solver optimize mathematical operators through numbers to minimize the residuals.

[@hp127]

Thank you, I nice introduction and examples of the possibilities.

[@flowy-moe]

Thank you very much! This is awesome :o

[@devfromthefuture506]

Amazing work!!

[@donggeon-kim]

Very cool! Respect!!!

[@G12GilbertProduction]

Entropical relatives with a minimal potential of power isn't not look foward under the Maxwell equations?

[@harikumarmuthu8819]

Why does a DL model be only converted to Math models, but not into an algorithm or combination of both. That means you can take a DL black box model into Algorithm+ math equation forming a code.

[@lakshminarayanansamavedham3770]

Cool but the genetic programming idea by Koza (1992) and several works following that come to mind.

[@sokhengdin8012]

Deep learning physics era is soon to be discovered...!

[@iamyouu]

Wow i would love to see more videos like this, so many videos were just theory.

[@myopinionman8199]

This is literally the holy grail... get a machine to reason scientifically and be able to communicate the results!

[@shawhin-music]

Very cool!

[@sanjeetchhokar5800]

This was great!

[@hacker2ish]

Why not try it on the 3 body problem?

[@TheDRAGONFLITE]

18:14 why is it rotated?

[@pauloffborba]

"low dimensional" is it like pure functions in funcional programming?

[@matthewjames7513]

Isn't this just the genetic optimization algorithm + machine learning?

[@jeroenritmeester73]

The fact that it is conceptually simple does not mean the applications can't be great. Most "big" scienctific discoveries are built upon thousands of "conceptually simple discoveries" like this. Edit: I always think of it like this: given enough time, could I have created this myself? Possibly, but unlikely. It is always easy to tell yourself "I could have done that" once you already know it.

[@matthewjames7513]

@@jeroenritmeester73 Thanks for the comment. I re-read my comment and realized it had a negative tone. I'm actually super impressed with this guys work! It's a huge step in the right direction. I love the idea of developing analytical formulas directly from data by using machine learning :)

[@InquilineKea]

Wolfram does both. Also probabilistic programming ppl

[@Didanihaaaa]

I like it. PINN and now fitting on Deep net!

[@allurbase]

Can this do particle physics?

[@evenaicantfigurethisout]

What are the implications of something being "low dimensional"? Please eli5

[@frun]

One needs highly fluid dark matter to understand this 🙂

[@WhenThoughtsConnect]

You compress the multivariable into a plane like dropping marbles onto a floor. And wait till they roll far enough so the space of vector fields that play with them doesn't interact.

[@brendawilliams8062]

Cool I roll marbles for a hobby.

[@brendawilliams8062]

I mean if you have 212. Then how many 101’s are there.

[@brendawilliams8062]

I say there’s 3

[@WhenThoughtsConnect]

If you are talking about a vector with 212 components then you will have 212 marbles in this plane before dropping through an optimized vector field. I think what he is talking about is the vector sums of the position functions of all the marbles interacting through these vector fields and averaging them to have a net movement to generalize the answer for that one particular component of the 212 vector.

[@brendawilliams8062]

@@WhenThoughtsConnect a 212 vector. Hi can it add more than 10072

[@dankkush5678]

nice one

[@JuanRamirez-di9bl]

So, will this thing finally figure out how to get a functional hoverboard?

[@copilco1]

nice

[@abderrahimzilali3293]

Wigerian Prior?

[@rctime8279]

TLDR; Math is dead.

[@JousefM]

Nice! 😏

[@brandonhuynh1966]

This is amazing. But dude you need to breath. Im getting out of breathe listening to this.

[@arnold-pdev]

Lol, I've been there. Just nerves and excitement. Remedied by practice.

[@drscott1]

Amazing stuff. You were doing great until you started talking about dark matter. Let’s call it what it is ‘ plasma and dust’.

[@anshumansinha5874]

Why is he making such sounds in between the explanations? That happens when you're thinking while presenting! Try to go through the presentation before recording!