thanks man i was finding it extremely difficult to understand the maths behind backward and detach (although i have doen it in my high school) because no one was explaining them in this depth.........love you 😍😍

This is what I was searching for months. I m so thankful Dr. Science for breaking down this concept for us

@DrDataScience

2 жыл бұрын

I'm glad you find it helpful!

Truly thankful to you. To the point without confusion. Thank you once again

Excellent videos and the textbook, deeply admire your contributions

Amazing as always!! Very helpful and valuable video!

This is what a proper tutorial should be. Thanks a lot. Subscribed

@DrDataScience

Жыл бұрын

Thanks!

thank you very much for uploading this video! very helpful!

14:50 x.grad contains the valuesd of partial{y} / partial{x} 17:50 x.grad.zero_() 25:00 gradient for multiple inputs -> multiple outputs. Since the Jacobian is a matrix, we need to input a 1-d tensor to get a valid vector-output. => But our loss function has been a scalar, so this is why I am not accustomed to this form. 34:10 explaining .detach(). => treat those as constants, not a variable that we differentiate w.r.t.

why do you need to multiply v vector to the jacobian matrix? and what is v vector exactly?

Thanks for the video, it really cleared up Pytorch autograd, now I will be making notes on this gold nugget

@DrDataScience

Жыл бұрын

Thanks!

First of all, I want to express my gratitude to you for the work you have done. There is one thing i want you to ask: why do we write the partial derivatives of the scalar function in the form of column? Whereas, following the logic of Jacobian matrix, it should be a row. Thanks in advance!

Awesome video! Thank you!

@DrDataScience

Жыл бұрын

Thanks!

This video deserves more view.

@DrDataScience

Жыл бұрын

Thanks a lot!

Thanks a lot.

great explanation! I hope it will get the likes it deserves

@DrDataScience

2 жыл бұрын

Thanks a lot!

Thank you sooo much! This finally clicked for me.

@DrDataScience

Жыл бұрын

I am glad you found it helpful!

Nice explanation. Found it from youtube recomendations

@DrDataScience

2 жыл бұрын

I am glad you found it helpful!

29:49 - As far as I understand in 'a.grad' should turn out [12., 18.]

Thank you

@DrDataScience

8 ай бұрын

Thank you!

thnks myfriend - in last section - whats is the z.sum ? what is the the (SUM) function for ? why yyou put the sum ?

way better than my prof...

@DrDataScience

6 ай бұрын

Thank you!

@danieleboch3224

27 күн бұрын

Loser.

Please Do cover a playlist on Graph Neural Networks (at least discuss all the basics and methods of GNNs). The internet world lacks quality contents on this topic

@DrDataScience

Жыл бұрын

Great suggestion! I'll work on it.

hi !! thanks for the wonderfull video :) can you please explain why vector v is 1?? and what is derivative w.r.t to self??

@DrDataScience

2 жыл бұрын

The derivative of any variable. let's say x, wrt itself, i.e., x, is equal to 1. That is why we use a vector of v of all ones. If for some reason, you want to exclude one variable from the gradient vector, you can then replace the corresponding entry of v with 0.

@arpit743

2 жыл бұрын

@@DrDataScience that does make sense thanks! But why do we multiply with v or ones what does the dot product of jacobian and vector v represent? Why do we multiply derivative of self with jacobian?

The way you define the y is different from what i am thinking. In first example, I thought we should define y as x**2 or in second one y as x. But if i define the y like this, I will get an error which say that it needs just one number not sequence of numbers.

@mahdiamrollahi8456

2 жыл бұрын

Oh I got it. But i did not get what v vector is?

No!

Fixed your broken web page that forces us to bend to your flaws.