Тёмный

#87 - ADELE MYERS - Regression-Based Elastic Metric Learning on Shape Spaces of Cell Curves  

Machine Learning Street Talk
Подписаться 148 тыс.
Просмотров 9 тыс.
50% 1

Опубликовано:

 

30 окт 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 20   
@103SideProjects
@103SideProjects Год назад
I clicked on this to see how smart I am. I’m clever at best, barely conscious at worst. Thank you for service, really smart people.
@paxdriver
@paxdriver Год назад
😂 You should listen to Michael Levin, Karl Friston, etc. Keith Duggar and Yannick Kilcher have some amazing insights on conscious systems and extrapolation vs interpolation too. There's so much amazing content on this channel dude, welcome to the rabbit hole lol.
@103SideProjects
@103SideProjects Год назад
@@paxdriver I have been listening to Levin and Friston non stop. This conversation is amazing: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-J6eJ44Jq_pw.html
@michaelwangCH
@michaelwangCH Год назад
If you feel too smart, you should not be on this channel - we learn because we are not smart enough to grasp the complexity of reality.
@theoreticalorigamiresearch186
@@michaelwangCH He is saying that he does not feel smart enough, as do I.
@jasdeepsinghgrover2470
@jasdeepsinghgrover2470 Год назад
To be honest after 3 minutes I felt numb. As if I didn't learn a thing doing ML for 4 years. Maybe her physics background is helping her in defining these but I have never tested my metrics so thoroughly ever.
@roomo7time
@roomo7time Год назад
Immense gratitude that you introduced an author of very interesting paper and interview video of the author.
@oncedidactic
@oncedidactic Год назад
Thanks for this interesting tidbit! (Very well explained by Adele!) I really like the general concept of sampling/transforming inputs to a different space before running ML “end to end” that’s just going to learn a similar transform anyway, or not and poorly imitate. You can complain about building in priors, but I think we’re still making progress doing exactly that for now, this paper being a perfect example.
@Jordans1882
@Jordans1882 Год назад
Wow. Generalizing the square root velocity function... Super cool. Will definitely check out this paper.
@jojo01925
@jojo01925 Год назад
Great explanation. From simple to more complex. Great channel. High quality, information dense, every word matters. Great interviewees. Super-smart beautiful people. Thank you
@LuddeWessen
@LuddeWessen Год назад
This is what really excites me about ML/DL - when clever people from other fields, and with other skillsets, continue into new weird directions!
@AndreiMellas
@AndreiMellas Год назад
Most excellent, Best YT channel on the Planet Earth!
@michaelwangCH
@michaelwangCH Год назад
Cool talk, but how well work with real data is an other question - we see how this idea can be improved. It is well-suited solution for specific problem, but it is not generic solution to solve geometric DL - a reasonable start in a new direction.
@tfburns
@tfburns Год назад
Glad to see some more diversity on this channel and in ML/AI generally :)
@tomoki-v6o
@tomoki-v6o Год назад
i think it can be used also for handwritten characters if we consider it as curves
@tavaroevanis8744
@tavaroevanis8744 Год назад
Or maybe ECG "curves"? That would be sweet!
@andreas0101
@andreas0101 Год назад
@orsonterrill4972
@orsonterrill4972 Год назад
Very cool. R^2 won't guarantee optimization, but that's only a distraction from the big ideas here, at the worst. A and B will be optimized for maximum R^2, and Rsqrd is not optimized for fit necessarily. Honestly, that R^2 part is something easily replaceable and inconsequential to the idea on the whole. If any haters had an issue with it, they're splitting hairs and missing the point.
@백영래-u3x
@백영래-u3x Год назад
🤞🤞🤞🤞🤞
@dr.mikeybee
@dr.mikeybee Год назад
Why in the world is this done using Riemannian geometry? At a cell's scale, this seems entirely unnecessary.
Далее
Michael Levin - Why Intelligence Isn't Limited To Brains.
1:03:36
The ChatGPT Paradox: Impressive Yet Incomplete
1:08:22
Просмотров 34 тыс.
МЖ. Может, папа - ты? 16.02.2023
40:03
Просмотров 204 тыс.
Leonel Rozo - Learning on Riemannian Manifolds
59:42
Просмотров 1,8 тыс.
Joscha Bach - Why Your Thoughts Aren't Yours.
1:52:46
Просмотров 49 тыс.
It's Not About Scale, It's About Abstraction
46:22
Просмотров 76 тыс.
Should Computers Run the World? - with Hannah Fry
36:05
МЖ. Может, папа - ты? 16.02.2023
40:03
Просмотров 204 тыс.