Hi! In week 4, the video “Forward and Backward Propagation”, we are introduced to the formula for calculating the derivative of the loss function with respect to the activation function of the previous layer (as part of the backward propagation): da[l-1] = W[l].T dot dz[l] Andrew in the video say…

Week 4 backward propagation da[l-1] derivation

paulinpaloalto July 24, 2021, 10:29pm 2

Here’s a thread with links to several sites that cover the math behind back propagation.

2 Likes

Topic		Replies	Views
C1_W4: Confused about da[l-1] Neural Networks and Deep Learning week-module-4	4	25	September 19, 2025
Neural networks Week4 Backprop da[l-1] proof AI Discussions ai-discussions	2	146	April 21, 2024
The intuition of db^[l]=dz^[l] and da^[l-1]=w^[l-1].dz^[l] Neural Networks and Deep Learning coursera-platform	4	811	May 27, 2023
Course 1: Week 3 (backpropagation intuition) Neural Networks and Deep Learning coursera-platform	21	5649	April 27, 2022
WK3 Backpropagation intuition formula demonstration Neural Networks and Deep Learning coursera-platform	4	586	June 27, 2022