Видео

나 유승준인데 나 너무 억울해

Thoroughly nice guy and so clever he's off the scale.

Pleasure to listen

Now that's data SCIENCE

Dude so smart he can create a universe in his spare time.

'tis the stuff that dreams are made of'

Terence sir, you can never become a clerk or shopkeeper as your hand writing is not great...but the whole world knows that if you put some effort you can easily solve the remaining few unsolved mathematical problems which mankind failed to solve upto this edge of time. Thank you.

Beautiful

Hey fields medal, or is it Nobel proze, for reminding people that Minkowski spacetime event singularities are every spacetime location and all geodesics that pass through that point intersect and the squeeze theorem integrated appropriately mens there is a continuum of events before the geodesics can intersect again. 😂😊

John, huh?

I loved it!

Eventually, we need to ask why we need to understand. AI will eventually solve problems without us needing to, or sometimes being able to, understand.

It is probably dumb or anyone else have trouble understanding folding analogy at 12:15? Is he suggesting that the planes are superimposed with one top of other? Or is he suggesting that sum of figure a and figure b lead to figure c? Can anyone help me in understanding it?

Thank you for your talk. I found it extremly interesting. I have some comment on your statement that simplicity is implied by utility : Differential Equations are very useful in describing our world, however they are at least in my mind not simple and to most people also not familiar. I would love to discuss about it !

Define these letters already

Which A.I. came up with that Theory? They usually hide inside Brains.

Best 25 minutes of my life.. Physician telling me a language model is just a chatbot refined.. I can do that. Let's go!

I really want to contribute to physics like Prof. Elliot😅, dude is phenomenal.

one of the best suggestions of the algorithm. there is a phrase widely used in education circles nowadays: 'Learning how to learn' and it is often criticised as human babies are already born with the ability to learn. But in the case of machines I suspect that is the way to go. They lack the genetic encoding we embedded in our biological systems for so long. Maybe we should treat these early machine learning models as their DNA?

The mental features discoursed of as the analytical are in themselves but little susceptible of analysis. --- Edgar Allan Poe To put it simply, it’s hard to understand why prodigies are the way they are

Great talk!!

Why does he have a giant stick, is he blind?

Yea it’s great if ur trying to use a system In a system to garner traction

Can change ringing be done with electric motors instead of bellringers?

i find it interesting special relativity wasn't an example of needing to fit the data. oh wait, i'm not, because there was no underlying data

Along with being so intelligent, he is such a likable guy. In the 4 minutes I've heard him talk, I already like the guy

I was pretty surprised to see this not actually purpose much of anything other than using tools to analyse patterns, three same tools that have been in use for decades. Is this a venture pitch? Throwing more processing at it helps, but doesn't "solve" anything on its own.

Your cat doesn't teleport?

Most likely a biological neural network

yooo, i'm so glad i came across this! i've been thinking about how neural networks can teach us about our own thinking and pattern finding; i'm glad there is discussion about it

33:16 Mark my words. There won't be any foundational-level model can achieve 5-digit of accuracy like the finite difference does for PDE, which was popularized three hundred years ago by Euler. Using the model alone (without the help of non-blackbox outer algorithms or second-order optimizer), no matter you have 1000 billion params, or what, never. 1000 years later our AI overlords will still use finite difference (maybe the BDF table will be learned by blackbox).

What happens if it’s trained on Schrödinger’s cat videos?

What makes him great? I don't found any of good quality between him!

Well more fun than AI churning out what are the most lethal substances. Modern nerve agent analog were in the outputs.

Very nice and interesting

Folding is an analogue to reducing dimensional complexity.

So wisdom is better than raw intellect. Got it. The more we know, the more it enhances anything else we do and think about. Not really a mystery, but nice to see the theory and it being proven. ML has always felt wrong to me because of the "toddler" he describes. Now that ai can know everything that the entire human race knows, of course it will start solving problems we can't think to solve alone with our own minds and data within. Who built our ai?

Damn wholesome mathematician.

Wow this is incredible and sort of confirms some thoughts I’ve had about neural networks and the compression of knowledge.

Go f yourself and learn to explain things in an orderly manner . You are a disgrace to humanity ...

Why is everyone recommended this video?

Interesting topic and well put presentation, however the speaker should practice a bit more its communication skills (not saying "I mean" or "like" every 2s) and stop reading the damn PowerPoint - I bet most viewers can read-. Again, it is a great topic and a good presentation. I will read his previous research after watching this.

Planets are older and dead stars.

Here's an April fools episode idea. Tales from the dark side episode where you discuss the extremely creative solutions you had to come up with while trying to do chase films on some UFO test object. Deliver it in a straight face with digressions on how it would be cool if / or how you are waiting to see the technology make it's way into the civilian market ect . For the photos have blurry images of birds or maybe say that the reason pictures are blurry is because UFOs are just blurry. Even when in the hangar

Quote (16:40): State of the art for symbolic regression... 25 days later a paper was released where so called KAN's where used to do symbolic regression, and I am pretty sure that this will be the state of the art. I know it was used only on small datasets and has some other flaws, but this is not worth talking about since we will make it work. They also refrence Miles Cranmer.

The AI field is hallucinating.

Biological or silicon network?

Wow; what a bridge from physics to number groups😊

Great presentation! My main takeaway is that we need a more unified approach to neural network models. Interoperability is important and can substitute for or even supercede the quality increase of pre-training.

even at 720p the quality is too poor to make out important details from his figures. Makes this difficult to follow.