Here is the video I watched: https://www.coursera.org/learn/neural-networks-deep-learning/lecture/6dDj7/backpropagation-intuition-optional I know calculus and totally understand how to compute the gradients of dL/dz^{2}, dL/dW^{2}, and dL/db^{2}, which have shapes R^1x1, R^1xn^{1}, R^1x1 respective…

Derivation of the gradients of W^[2], and b^[2] in the 1 hidden neuron network

saifkhanengr March 17, 2025, 1:36pm 2

Check this YouTube guide of Eddy Shyu and this chain rule.

1 Like

Topic		Replies	Views
The intuition of db^[l]=dz^[l] and da^[l-1]=w^[l-1].dz^[l] Neural Networks and Deep Learning	4	784	May 27, 2023
W2_A1_Calculating gradient descent with variables Dw and db Neural Networks and Deep Learning	5	1020	December 8, 2023
W3_A1_Derivative for hidden neural layers (Backprop) Neural Networks and Deep Learning	5	608	February 9, 2023
Gradience Descent Backpropagatin Calculation Neural Networks and Deep Learning	1	624	January 24, 2022
How did we calculate dz[2] in Backpropagation Intuition (8:34)? Neural Networks and Deep Learning	1	645	March 6, 2022