L6.2 Understanding Automatic Differentiation via Computation Graphs

  Рет қаралды 11,915

Sebastian Raschka

Sebastian Raschka

Күн бұрын

Пікірлер: 12
@karimelkabbaj
@karimelkabbaj Жыл бұрын
Thank you very much for this simplified explanation, i've been struggling to understand it until i found this master piece.
@SebastianRaschka
@SebastianRaschka Жыл бұрын
Nice, glad to hear that this was useful!!
@manuelkarner8746
@manuelkarner8746 2 жыл бұрын
thaaaank you, finaly I understand this perfectly (& can know repeat it for myself) explaining backpropagation my lovely proffs always said "then this is just the chainrule" & skipped any explanation for calculating (complicated) toy examples I knew the chainrule, but in the backprop context it was just to confusing ________Anway, got a question: at 12:23 you said tehcnicaly canceling the delta terms is not allowed -> could you elaborate on the math/why or point me to some ressourece explaining this ? Intuitively I always thought canceling delta´s is strange/unformal but I dont found out how this delta notation stuff fits into "normal" math notation :)
@SebastianRaschka
@SebastianRaschka 2 жыл бұрын
Nice, I am really glad to hear that! And yes, I totally agree. When I first learned it, it was also very confusing at first because the prof tried to brush it aside ("it's just calculus and the chain rule") just like you described!
@nak6608
@nak6608 Жыл бұрын
Love your textbooks and your videos. Thank you!
@736939
@736939 3 жыл бұрын
17:27 In the formula on the top-left (as I understood) there is no sum, but stacking (or concatenating), then why should we add the results in different paths during the backward chain computation? Is it always work like this - just produce the sum in the chain when there is a concatenating????
@SebastianRaschka
@SebastianRaschka 3 жыл бұрын
Sorry if this was misleading. In the upper left corner, this was more like a function notation to highlight the function arguments. Like if you have a function L that computes x^2 + y^2, then it's basically like writing L(x, y) = x^2 + y^2. There is no concatenation. With the square brackets I meant to show that sigma_3 contains also function arguments. I just used square brackets (instead of round brackets) so it is easier to read, but now I can see how this can be confusing.
@736939
@736939 3 жыл бұрын
@@SebastianRaschka Thank you very much.
@mahmoodmohajer1677
@mahmoodmohajer1677 11 ай бұрын
thanks for pulling up this video.
@Gzzzzzz111
@Gzzzzzz111 Жыл бұрын
YOU ARE GOATED!
@Epistemophilos
@Epistemophilos Жыл бұрын
At 11:27 it gets confusing because you switch the terms around. Otherwise, very nice video.
@АртурЗарипов-ю9п
@АртурЗарипов-ю9п Жыл бұрын
Thank you very much!
L6.3 Automatic Differentiation in PyTorch -- Code Example
9:03
Sebastian Raschka
Рет қаралды 7 М.
What is Automatic Differentiation?
14:25
Ari Seff
Рет қаралды 120 М.
Sigma Kid Mistake #funny #sigma
00:17
CRAZY GREAPA
Рет қаралды 30 МЛН
Enceinte et en Bazard: Les Chroniques du Nettoyage ! 🚽✨
00:21
Two More French
Рет қаралды 42 МЛН
Chain Game Strong ⛓️
00:21
Anwar Jibawi
Рет қаралды 41 МЛН
Neural Networks 6 Computation Graphs and Backward Differentiation
10:31
From Languages to Information
Рет қаралды 31 М.
PyTorch Autograd Explained - In-depth Tutorial
13:42
Elliot Waite
Рет қаралды 112 М.
The Most Important Algorithm in Machine Learning
40:08
Artem Kirsanov
Рет қаралды 553 М.
Intuition behind reverse mode algorithmic differentiation (AD)
13:17
Lecture 6: Backpropagation
1:11:16
Michigan Online
Рет қаралды 108 М.
Automatic Differentiation: Differentiate (almost) any function
8:41
Lecture 4 - Automatic Differentiation
1:03:35
Deep Learning Systems Course
Рет қаралды 17 М.
Automatic Differentiation
19:33
Computer Graphics at TU Wien
Рет қаралды 10 М.
Hardy's Integral
13:47
Michael Penn
Рет қаралды 15 М.
L8.8 Softmax Regression Derivatives for Gradient Descent
19:40
Sebastian Raschka
Рет қаралды 13 М.
Sigma Kid Mistake #funny #sigma
00:17
CRAZY GREAPA
Рет қаралды 30 МЛН