Відео

One must stress what you say at the end of the video at 28:20, that although AlohaFold 2.0 can predict native confirmation of an amino acid sequence, there are other contributing factors, and the algorithm isn’t able to answer the why, nor how proteins find their native state out of the vast combinatorial complexity of native confrontation structures. Levinthal’s Paradox.

After going through most of the UA-cam videos on this topic. This one was one of the best out of all. Very clear and crisp explanation. Thank you ❤

4:00

subscribed

1:00

Amazing

Great breakdown and links for additional resources

Bro! you were soo ahead of your time! Like Scooby Doo

This is so good. Thank you!

GOAT

12:28 what did you use to connect the machine learning to a 3d model?

This is gold!!

Great work

6 years ago and I now use this video as a guidance to understanding StableDiffusion

This is cool, but after the third random jumpscare sound I couldn't pay attention to what you were saying--all I could think about was when the next one would be. Gave up halfway through since it was stressing me out

this guy too hadnsome, itlain hands

Rest in peace Tishby

This is a marvel. I read a book with similar content, and it was a marvel to behold. "The Art of Saying No: Mastering Boundaries for a Fulfilling Life" by Samuel Dawn

feel like beta should be decreased as training progresses and the learning rate decreases too. Sounds like hyperparameter tuning though

Figuratively exploded*

Five years later and RL is a dream's product. Nothing was really solved in real world. I think there's pratical areas of IA better than that.

Great video, and the algorithm is finally recognizing it! Come back and produce more videos?

This kind of well-articulated explanation of research is a real service to the ML community. Thanks for sharing this.

Very good video

If you dont understand this explanation, the fault is on you.

Lmao this must be a joke. Anyone who supports this theory has no understanding of the exponentially nature of how AI learns.

Excellent video

Very interesting. It looks like Nature is alive -very much alive.

Glad to see that human biological computer network is still much efficient than machine with artificial neural network.

Excellent educational video on artificial and deep neural network learning.

Excellent video education on bio-molecular technology.

Another amazing video ... thanks ... any chance of some new videos coming out on recent papers?

5:03 "to test the presence and influence of different kinds of human priors" ... this is pretty cool ...

3:12 This reminds me of Chomsky's critique of AI and LLMs. Any comments?

Thanks for sharing this! I may be misunderstanding something, but it seems like there might be a mistake in the description. Specifically, the claim in 12:50 that "this is the only region where the unclipped part... has a lower value than the clipped version". I think this claim might be wrong, because there could be another case where the unclipped version would be selected: For example, if the ratio is e.g 0.5 (and we assume epsilon is 0.2), that would mean the ratio is smaller than the clipped version (which would be 0.8), and it would be selected. Is that not the case?

Great Video!! I just watched 4 hours worth of lectures, in which nothing really became clear to me, and while watching this video everything clicked! Will definitely be checking out your other work

I didn't forget the subscrip, but you seems to forget updating

Why have you stopped doing wonderful tutorial? I wish you would have continued your channel.

extremely amazing, thanks for creating this incredible vedio

The term "activation" in the context of neural networks generally refers to the output of a neuron, regardless of whether the network is recognizing a specific pattern. The activation is indeed a numerical value that represents the result of applying the neuron's activation function to the weighted sum of its inputs. Just posting here what ChatGPT told me, because the definition of "activation" in this video confused me

Thank you! This was comprehensive and comprehendible.

Very very good video, thank you

thank you sir! appreciate the effort that went into this video

THANK YOOOOOOOU I was reading that article you commented on and I couldn't understand for the life of me how they were generating those images, so tysm ;-;

... huh?

fiiiinnnaaaallly after tons of googling, I finally fund a USEFUL video that accually EXPLAINS how to reward the agent, and not just saying: 'oh u just reward it'

As a person shifting career from data science to bioinformatics, I found this video very helpful & amazingly animated! Hope to see more stuff related to computational biology & AI applications in that

you are great bro

Man that's call standarization!! Wtf?? Reparametrization trick???

Incredible work!