Видео

Hi @CodeEmpoium, Thank you very much for the video. It is very useful and well done. I just have one clarification. When you draw the Gaussian distribution corresponding to the point Xi (01:10-01:30), it seems that you make the peak of the curve coincide with the intersection of the interpolating line. Usually, it doesn’t happen this way; the peak is at the intersection of the vertical line passing through Xi and the interpolating line. As shown in this image: towardsdatascience.com/probabilistic-interpretation-of-linear-regression-clearly-explained-d3b9ba26823b Is that correct?

absolute banger! well done

Could not get anything from this. too complex

How is it 20:1 for alexnet 👀

great explanation.

great video thanks question ... in the third question ... how do sample subset of keys, queries "depending on importance"

Good explanation!

lmk if they say

the best video so far

you're a clear, calm explainer.

Nice explanation

well explained , you made it look really easy !

what book is that

Vsauce plugin 😂

1-B 2-ABCD 3-C are these answers correct?

1-CD 2-D 3-D

1 - B, 2 - B, 3 - C. Are these answers correct?

That's not Pong.

1 - A 2 - ABC 3 - A Are these answers correct?

(1) supervised fine-tuning (SFT), (2) reward model (RM) training, and (3) reinforcement learning via proximal policy optimization (PPO) on this reward model explain me

Great work ❤

I have seen so many transformers videos but this one is outstanding, I also want to request you to make a video on vision transformers too❤

Nice video, well explained. Question, why would I use one or the other? Are there advantages or disadvantages?

Is it your voice or what ai you use ?

what does x and y represent in the graph you use to show the cats and dog points ?

thank u so much

Really Appreciate Your Efforts. Love from Gujarat India.

The best explanations on transformers that i have seen!

according to dr. c. k. raju calculus was stolen from india

You are my new favorite channel

The video is informative and good. but stop saying quiz time in an annoying way

Super clear, thanks!

1997

Easy

1. either of MSE or MAE as both are used as loss functions for regression. 2.A,B,C 3.A are these answers correct?

Valeu!

it was a great tutorial will be back soon

Thanks for a very informative explanation. This seems like a bit of a step up in complexity from earlier videos, so I suspect some viewers of earlier ones might not make it to the end of this one. I think the Quiz answers are A B B. Presumably this Probsparse approach is useful in other situations (image processing springs to mind) as well as time sequences.

you are the best on the youtube for the transformer all the best

Hey I am not able to access the links you have provided under Math courses and other related courses

Hey I am not able to access the Math courses link mentioned in description. Could you please update those links

@4:38 are you sure d_q is the number of total time steps? I think it's supposed to be the dimension of the query & key.

In the final video are you going show an example when you feed data into the model and the interpret the output. It would be good to see any prepressing of the data to get it in the right format to feed into the model. I'm keen to use this model for a timeseries forecasting exercise 8 timesteps ahead.

Can u tell an interactive model of AI neural network for school project.. And ur videos are nice and I understand easily.. Pls tell

All this hindu Indian scientists where really selfie to keep there studies and research to a certain group And when someone from West discover out the completely same thing like after 200 or 300 years they started saying "no we discovered it hundreds of years ago " . So why don't you spread that knowledge Because of people like this the your science knowledge and this so called modern world is 100 years back in time

Very well explained

Why this is so Underrated, this should be on every one playlist for linear regression. Hatsoff man :)

wonderful explanation!!!

C

B