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
Week 4 Video: Forward and Backward Propogation Neural Networks and Deep Learning	1	562	July 10, 2021
Didn't get the derivation Neural Networks and Deep Learning week-4	4	25	October 14, 2024
Week 3: computing derivatives for shallow network Neural Networks and Deep Learning	2	681	January 26, 2022
Assignment Building NN C1 Week 4 Neural Networks and Deep Learning	11	621	August 16, 2022
Course 1 Week 4 programming assignment #2 error Neural Networks and Deep Learning	9	574	September 30, 2022