[friebetill]

I found this 13 min explanation very helpful in understanding backpropagation (https://youtu.be/c36lUUr864M?t=2520).

First he explains the necessary concepts:

1) Chain Rule

2) Computational Graph

Then he explains backpropagation in these three steps (first in general and then with examples):

1) Forward pass: Compute loss

2) Compute local gradients

3) Backward pass: Compute dLoss/dWeights using the Chain Rule