ICLR 2021 Keynote - "Geometric Deep Learning: The Erlangen Programme of ML" - M Bronstein

wonderful work.

Poor man, only after reading the theory of the prehistoric midwives, they are able to understand nature science. Historical coins can prove, that these women knew already EVERYTING what is here presented. These men only could figger out these things after copying the UNIVERSAL SOUNDHELIX! The best joke will be that even these soundhelix will show us this plagiarism! Time will show it. At this time chatGPT was not presented to the public. The chatbox will show the truth of these presentation.

A wonderful exemplar of a "Renaissance" in Information, beautifully shared and affording us an "On-Ramp" towards collaboration. Its interesting to speculate where Geometric Deep Learning's impact will help help next after the more Physiology context of "biologic science and drug design for Health". Perhaps the Psychological domain of cognitive sciences in designing "Active inference" [Friston] algorithms (for Happiness) guided by Free energy and hierarchically partitioned Markov Blankets to reach those who suffer and demise in the face of their mental environment. If such and optimisation ( ie minimisation of cognitive dissonance via a map) is available for an individual ( in their cognitive coordinates ) on the cognitive manifold then perhaps there hope for helping their cognitive neighbour. In essence: "Mind Maps, an Atlas of one to many on the Cognitive Manifold".

Update: Are you and Elon on good terms?

this video requires PhD in math holder to go through it, not for me

Good talk but I always find talk about "detecting fake news" to be kinda suspect. You can detect the affiliation of a source of news but that doesn't mean you can tell whether it's "fake" or not

,,, jk comnts :: simplify to finally capture complexity!?! ...

,,, jk comnts :: geom DL +-=decod language for AI yields sentience!?! ...

Absolutely Amazing Prof Bronstein!

Thank you for such an amazing piece of content.

Wow. Just. Wow.
The quality of this presentation is incredible. The animations enabled me to grasp concepts (almost) instantly. So incredibly helpful for my current paper. Thank you ever so much for the money, time, and effort it took to produce a video of such exceptional quality.

checking for fake news by using bias and propaganda as a guideline doesn't produce an accurate model

Wow! this is an excelent presentation, I guess your classes are something like this, and your students are very lucky to have you as a professor.

This is amazing.

It's year 2030. MLPs are SOTA on all domains imaginable to human mind.

MLP AGI whispers: Michael didn't mention me in his ICLR keynote.

Paperclips.

absolute gold

very good coverage. thank you, Prof. Bronstein

Absolutely great presentation! What software was used to create these animations? :) Thanks

Thank you for this great presentation and for sharing it with the common public.

This is amazing sir..Hopefully this will motivate the student community to take up mathematics very seriously

Awesome!

Full fledged AR and VR products are gonna be launched soon is one of the takes. Metaverse is here

Great presentation. Can you tell me how the software you use to animate the graphs?

I am quite excited about this field. Traditionally the innovation in biotech engineering was hampered by ethical concerns. With this technique we can quickly innovate without any political ramification. This is quite akin to the growth of internet itself

Imagine how much time the presenter has spent preparing this presentation.

awesome!!

Oh yeah, RealSense, I've been working with them in image recognition, trying to build something similar to Complex Yolo, but in a more engineering way. However, the quality was not suited for the harsh conditions we were exposing the devices to (pig stall). It was also the time when the first extensive neuronal network libraries became available, and I've said that in a few years the tech calibration of the camera will be just replaced by a neural network. And, broadly speaking, that's what drives my current research.

My old math teacher would break out in a sweat of disbelief seeing that higher mathematics can be used to recognise cats !

Amazing. I'm speechless.

Dont use sov un referenced etc. It is insulting to those 66 million who where slaughtered for the benefit of the global elite.

Such an inspiring presentation!

Presentation quality is stuning

this is amazing

This is amazing. I hope you make more videos like this again!

Is one of the possible domains of GDL going to be in any instance of a dynamic system? For instance not just proteins but interactions between molecular pathways? Or meme propagation networks?

Thanks

Great work... this has the chance to advance DL considerably, especially detecting "intrinsic features" which will solve many existing problems
This is real science !!! Thumbs up!

The only thing I dislike is the vile figurative analogy showing the researchers as socialists - abhorrent.

I'm in love with this presentation format! Would you consider sharing the Illustrator and After Effect project files? I'd like to learn how to do this and have no clue where to start!

Very nice presentation

Well done! Clear and visual! Please more like that! Thanks a lot!

Time base from data to force altering lead to transformation and amphomorism. Like water it remain water in different temperature so it survival all economic, political, and religious condition and remain an kind, compassionate, and creative wise human

It takes a semester for us to comprehend this marathon talk, Sir. Great visionary talk. Thank you Sir

Such an amazing lecture! Thank you very much :)

The nerve of this guy. All this talk about deep learning and he didn’t cite Schmidhuber even once!

mathematically beautiful, but I'm not sure my brain uses gauge symmetry to figure out the 3d object which I look at...

This presentation is as great as the talk itself. What software did you use to create the presentation graphics?

I wasn't sure at first as to how you wanted to connect the different geometries with deep learning , but as the video went on, I could see what you meant. And now, I am thinking about how it can be applied in emotion classification project I'm interested in. Thank you for the general insight, It would be incredibly awesome if you can attach some git works.

seems like a very interesting talk, although not very tangible for newbies or non-math people :(