Видео

why no positive face expressions?

When AI discovers this, and uses it to predict human reactions, it will play us perfectly

DAMN MAN YOU ARE UNDERATED. You deserve at least a 100k subs. You got 1 more from me! Do remember us when you get big!

It's not enough to DISPLAY emotions! There HAS to be a active inner state also!!!

I ALWAYS like to keep up with the latest on the tech 😁👍

This is such an underrated paper and video. Thanks for uploading.

Can't access the project website! Please fix

Man I guess even us mathematicians are not safe from AIs automating our job 😂

I thought finite dimension Koopman operators cannot express multistability. I'm surprised that the duffing and magnetic pendulum cases somehow work. Are they truly multistable (asymptotically) and also robust to small perturbations in the state?

Great video! I’ll be checking out your paper in detail later today. I had a quick glance at it and I have a few questions and a suggestion. I’m curious: around 13:09, was the change of coordinates that your method learned for the Hodgkin-Huxley model a time varying change of coordinates? Also, did the change of coordinates depend on the initial condition? Last, to the best of my (weak) understanding, the Hodgkin-Huxley model has inputs. If I’m right, how did you handle those? Also, typically, the condition for “asymptotic” (as opposed to “Lyapunov”) stability is that “\dot{V}(x) < 0” (as opposed to “\dot{V}(x) \leq 0”). If you are getting away with a negative semi-definite Lyapunov rate by using a LaSalle’s invariance principle based argument, you should state that in the video and in your paper. FYI, I’m using definitions as they are given in Khalil’s textbook. If my critiques are coming from a difference of terminology, please disregard. Also, I love the figures! Very compelling!

Nice video, showing complex mathematics, in a friendly way. Personally, I think the most important skills to have is an understanding of the dynamical system, building an intuition and then forecasting behaviour. Automating it is an extra bonus in my opinion, which will help reduce the time between understanding the dynamics and forecasting results. But the hard skill here, is building the intuition for dynamical systems. Great work, cheers.

0:24 fingerprints pattern...

The hodgkin huxley approximation is huge for neuromorphic computing. linear approximations mean closed form solutions are applicable, reducing the number of calculations needed during spiking neural network inference. if you'd like to know more, please get in touch with me.

I don't have to understand all of it, to understand the beauty of it.

Tremendous research and thanks for sharing to the global robotics community

Would this be applicable to the Einstein field equations by any chance?

This is soo cool, I would love to see how this compares to more conventional RL methods on MDPs or POMDPs, or PINN approaches (maybe this can also be thought of as a PINN?), especially it would be interesting to compare the network sizes of various methods. I would be interested to help integrate this within Nvidia Isaac sim for virtual world models. I briefly played with and encountered Koopman analysis when I did a project with wavelet feature representations and I've also thought about this potential.

dx/dt = f(t) = f(x)

Great video!

this is the area I'm interested in! I'm only a freshman in college, so I was looking everywhere for experts who is doing research in this field. RUclips algorithm really works out for me this time

Can you please fix the SSL on your website so that we could take a look at the code?

This is sick, amazing!

amazing work

So cute and cool!

Paura anche se fossi piena di soldi non comprerei mai un robot che mi fa solo paura.😮

This is really great work and progress made! I look forward to seeing more developments!

it seems like everything has already been invented

all robots must also exist in the parallel three-dimensional world as well as our own

give it some big meaty cheeks

That's sooo cool! I love stuff like this, and I especially like the integration of passive dynamics, since that seems to be often neglected. Heck, I didn't even know that was the word for it until seeing this video... Great work!

can i buy that?

Using the 3D bounding box of objects for positioning with a bin packing algorithm, or even just using the 2D bounding box information in the xy plane to perform bin packing, could solve this problem. Why design such a complex system to address such a basic issue?

They have knees but don't use them at all. Their joints are too big and blocky, making them look awkward instead of cute. Making them bigger leaving the hardware the same size might look better. Overall nice concept, but needs a lot of work still.

tremendo, tremendous, a step forward to create expected movie-robots hahah, good video

Very insightful.

This is awesome ❤ Lately ive been thinking that i wouldn't want a humanoid robot in the house, but would definitely go for a small monkey like robot, like an ai animal companion haha

awesome

You could also make it produce sounds from the visual clues.

The internal representation(s) of self and outer world into which we enact thoughts experiments, for example imagination and anticipation, is present in humans and could be expanded in future works like this. Also pursuing goals through action so internal networks that can learn motivation, desires, repulsion. are needed to get to conscience.

Good stuff!

Incredible.

C'est peut-être la découverte du siècle le potentiel est presque infini !

Incroyable découverte! Hâte de suivre l'évolution de vos recherches!! Votre IA semble très prometteuse 😍

This is insane. Congratulations!

I fell in love with this concept back when I used Nutonian Eureqa (and lots of good pointers from M Schmidt). This is next level! There are few ML endeavors more beneficial to humanity than discerning physical theorems directly from data with no initial primer. Very excited to see where you take this next. Makes me want to use my physics education a bit more and get coding!

Total genius, I love that fire has by far the highest ID.

Oh that's just fantastic work!