Hi, Thanks for reading my message. My question is related to the implementation of linear_activation_backward function. In this assignment, we have multiple ReLU activation functions in the hidden layers and one sigmoid function in the output layer. There is a function provided for the backward …

Hello @nfattal , [image] Note that Z and A are vectors and all multiplications are element-wise. Therefore, we need Z to compute g(Z), and we need dA to compute dZ. Cheers, Raymond

Thanks Raymond and Rashmi for the prompt reply. I will review the answer provided and comment back if needed. Thanks,

Just a follow on to that, I understand the equation, but at layer L (the output layer), DZ = A[L] - Y. It is not the equation you kindly pasted. That is what we used also in week’s 3 assignment and the course material. DZ[L]=A[L]-Y when calculating the derivative at the output layer. Thanks,

My deviation was explaining these questions: [image] nfattal: What is sigmoid_backward function calculating then? and why does it need dA as a parameter and the activation_cache (which is Z in this case)?

[image] nfattal: That is what we used also in week’s 3 assignment and the course material. DZ[L]=A[L]-Y when calculating the derivative at the output layer. The point is that sigmoid_backward and relu_backward are calculating the formula that Raymond shows. Remember that these functions are …

@paulinpaloalto , @rmwkwok Thank you gentlemen for the time and effort you put in replying to the queries. Understood.

Gentlemen, Just thought of mentioning that it may be clearer and may result in fewer questions on this topic if we show the derivation in the class notes posted in the course material. Please see the derivation added to the course notes (attached file) which is basically the same as the link provi…

Sigmoid Function in Layer L

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

Rashmi January 26, 2023, 8:54am 3

Dear NFattal,

There’s a similar query in this link. It would justify most of your doubts.

Topic		Replies	Views
Course 1 week 4, assignment 1, exercise 8: linear activation backward Neural Networks and Deep Learning coursera-platform	4	667	February 11, 2022
Confusion about Calculating dZ^[l] Neural Networks and Deep Learning coursera-platform	3	833	October 26, 2022
dZ for sigmoid in linear_activation_backward Neural Networks and Deep Learning coursera-platform	6	745	October 27, 2022
W4_A1_Ex-8_Linear_Activation_Backward_𝑔′(𝑍[𝑙]) for relu & sigmoid Neural Networks and Deep Learning coursera-platform	1	546	June 9, 2023
W4_A1_Computing Activation functions in Linear Activation Backward Neural Networks and Deep Learning coursera-platform	7	533	August 14, 2023

Sigmoid Function in Layer L

Related topics