Видео

Thanks a lot for sharing us how things work and the updates of our time

are you writing on a glass board?

thank's 4 all u'r time & effort! best regards Steve!

Very ineffecient… stick to quantum… Virtual photon replication is the future. Swinging heavy electrons drains the powergrid.

I'm reminded of Prof Tadashi Tokieda's "kendama" toy video - would make a fun example. ruclips.net/video/TkGawXjsltc/видео.html

very cool!

nice now try to balance a double pendulum

I thought he meant Prime from SSB 😛💕

Man I miss this bring it back 👄😻👅

What is deflection

What is deflection

The 🐐 PERIOD!

Played the intro a couple of times - Nice segue!

Why is it implicit that x(k+1)=x(k)+f(x) is Euler integration ? Can be any integrator depending on how you build f(x), Runge Kutta for example f is f(x) =h/6*(k1+2*k2+2*k3+k4).

Lifesaver

Will there be problem if the real system is chaotic?

Many thanks for shearing...

Is not supposed to be i + j + k at 10:48 of the video? What I missing?

I am a video editor. If you need any help related to video editing you can contact me. I will share my portfolio

That's weird, the loss function you said in the video which is different from your paper

Laplace transform and inverse Laplace transform are just Linear Transform forth and back. The same as Fourier transform, they are essentially Linear Transformations.

I cant download or open tem PDF book. Someone are having the same problem?

Wow i just relearned SVD in 13m whereas if took me hours in undergrad.

at 44:00 I think this inequality can be deduced using Taylor series expansion up to 2 terms for cosine

minute 41:00 I think the trick is |R-a| = sqrt((R-a)^2) wich leads to sqrt(R^2 - 2aR + a^2) If theta = pi, the inequality becomes equal, so true, but if theta is different from pi, the term 2aR cos(theta) < 2aR which is also true. Then you're right

What about periodic functions? Is there a way to get nice approximations with neural networks?

I'm highly critical of so-called RUclips "educators." I just watched several on SVD from MIT and Stanford, all of which were garbage. But this... this is art in its purest form. You are a scholar among scholars! Absolutely beautiful to watch unfold. Thank you!!!

Hello! Do you have the example of double mass, spring and damper system?

As a Chemical Engineer that studied CFD in grad school turned Data Scientist, I absolutely love this and the fact that there is active research in the intersection of physics and AI.

what id really mass energy and momentum created then how will gauss divergence theorem work?

This is awesome! I am so stocked about how they have found a 15D linear system with integer sparse off-diagonal matrix approximating Lorenz attractor with such an accuracy. It is a pure joy contemplating this mathematical elegance

It's not just a log function that has levels. The numbers themselves have levels. exp(i t) = exp(i (t + 2 pi k)) for all integer k It seems to me that any complex valued function also has levels. Why is the Log function singled out as special? Is it because it has a singularity?

epic lighting. subscribed.

Your words of choice are easy to understand and make the lecture sounds fun! Thankyou! Will sit for my final this 29june pray for me🙏

9:21 so you change the lower bound to 0 because the lowest value we can obtain from solving the integral is now 0, rather than negative infinity, since you've defined it to be that way using H(t)? Is that about right?

You outdid yourself as usual

Amazing, Than you

Amazing, Thank you

2024, still the best.

Fantastic video! Do you have any references for the mathematics behind the continuous adjoint method?

STEVE I ABSOLUTLY LOVE HOW SHARP AND CLEAN AND PACKED FULL OF INFO YET STILL DIGESTIBLE EVERYTHING IS!! You are my favorite teacher. I am a self learner and you are GOD MODE for that. PS: please do a video on why all power series are Taylor series (without borel heavy machinery if possible or by using borel but breaking everything down)!

Why is EVERY power series a Taylor series (without having to use heavy analysis stuff I don’t understand)!?

You know that it is going to be a great lecture series when Eigensteve is teaching you about eigenvalues and eigenvectors

tbh understanding his videos is very difficult, IMO he explains badly. Like 14:14 is the first more complicated part and I don't really get what it is about. I wouldn't understand ResNet from his explanation either if I had no prior knowledge about it. He just assumes that I am some expert in math and DLs

suposse we have a discrete time signal x[n]=exp(jwn) and it is periodic with N. then exp(jw(n+N))=exp(jwn) thus exp(jwN)=1. because 1=exp(2(pi)k) where k is an integer, equation w=2(pi)k/N must hold. if N is chosen to be pi ,which is not an integer, x[n] is not periodic. consequently, has infinitely many unique values. In addition, for x[n] to be periodic, w must be some multiple of pi (true when k and N are integers).

I'm so much very grateful for these videos you make. Keep on the good work.

This is so technically correct, and simultaneously so obtuse, that my intuition fuse has melted. Please consider redoing this as 3D pseudo visualizations of data subsets.

tim cook?

How can sigma be invertible when it's a rectangular matrix?

This seems like you are changing your loss function not your network. Like there is some underlying field you are trying to approximate and you're not commenting on the structure of the network for that function. You are only concerning yourself with how you are evaluating that function (integrating) to compare to reality. I think it's more correct to call these ODE Loss Functions, Euler Loss Functions, or Lagrange Loss Functions for neural network evaluation.