Can anyone explain why db^[l]=dz^[l] and da^[l-1]=w^[l-1].dz^[l] in week 4 and the video “Forward and backward propagation”? Thanks. [image]

The intuition of db^[l]=dz^[l] and da^[l-1]=w^[l-1].dz^[l]

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning

paulinpaloalto May 21, 2023, 2:58pm 4

We are doing matrix calculus here. If you are not familiar with that, please see the links on the thread I gave earlier. E.g. this one that is pointed to from that thread.

Topic		Replies	Views
W3_A1_Derivative for hidden neural layers (Backprop) Neural Networks and Deep Learning	5	598	February 9, 2023
WK3 Backpropagation intuition formula demonstration Neural Networks and Deep Learning	4	555	June 27, 2022
Backprop derivative after output later - Course 1: Week 3 Neural Networks and Deep Learning	4	597	June 22, 2024
Week 3: Why dZ^[1] = W^[2]T dZ^[2] * g^[1]'(Z^[1]) Neural Networks and Deep Learning	3	868	February 13, 2023
Course 1: Week 3 (backpropagation intuition) Neural Networks and Deep Learning	21	4775	April 27, 2022

The intuition of db^[l]=dz^[l] and da^[l-1]=w^[l-1].dz^[l]

Related topics