Please teach me!!! In week3 neural nets with one hidden layer, I learned dZ2 = A2 - Y. This is a output layer. But in week4, I learned in output layer we calculate dZL = dAL .* g’(ZL). Why has it changed ?

The second formula is the general case of that calculation that works at any layer. The first version is what you get if you apply the second formula to the specific case of the output layer because of derivatives of the cross entropy loss function and the sigmoid activation function. That derivatio…

[image] paulinpaloalto: 𝑑⁢𝑍[𝑙] =𝑑⁢𝐴[𝑙] ∗𝑔[𝑙]′⁡(𝑍[𝑙]) any suggestions how this can be derived?

That is beyond the scope of these courses, but there are lots of other webpages that cover the calculus behind all this. Here’s a thread with pointers to get you started on that. I got that link from one of the topics on the DLS FAQ thread , which is worth a look just on general principles if you hav…

I don't know the difference between dZL = AL - Y and dZL = dAL .* g'(ZL)

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

nagesh.bs March 3, 2026, 3:33pm 4

any suggestions how this can be derived?

Why g' in 𝑑⁢𝑍[𝑙] =𝑑⁢𝐴[𝑙] ∗𝑔[𝑙]′⁡(𝑍[𝑙]) and not dg?

Topic		Replies	Views
Confusion about Calculating dZ^[l] Neural Networks and Deep Learning coursera-platform	3	860	October 26, 2022
dZ[1] derivation Neural Networks and Deep Learning coursera-platform	1	758	November 4, 2021
Could someone help explain about this to me? Neural Networks and Deep Learning coursera-platform	1	650	May 24, 2023
How we got derivative of dz[1]=w[2]T.dz[2]*g[1]`(z[1]) Neural Networks and Deep Learning week-module-3 , coursera-platform	1	264	May 7, 2024
Confused at how the formula of dz in hidden layer was deducted Improving Deep Neural Networks: Hyperparameter tun coursera-platform	1	653	April 4, 2022

I don't know the difference between dZL = AL - Y and dZL = dAL .* g'(ZL)

Related topics