Hi, “My” rnn_backward function runs well. Nevertheless, I don’t find the attempted result. Here is the result :slight_smile: gradients[“dx”][1][2] = [-0.15028183 -0.34554547 0.02071758 0.01483317] gradients[“dx”].shape = (3, 10, 4) gradients[“da0”][2][3] = -0.17268893183890754 gradients[“d…

@CyrilleB Please read the 1st link in my previous reply and fix rnn_cell_backward.

Thank you. I fhave found my mistakes… 2 : I added da_prevt and so weel-understood why. I had a bad initialization of da_prevt because I added it one more dimension… I thank you very much for your help ! Have a nice day. Cyrille

Trouble results delivered by rnn_backward

Course Q&A Deep Learning Specialization Sequence Models

balaji.ambresh May 15, 2024, 2:45pm 2

If 1 and 2 don’t help, please click my name and message your notebook as an attachment.

Topic		Replies	Views
D5W1 A1 Assignment Exercise 6 rnn_backward need help Sequence Models coursera-platform	2	820	February 14, 2023
All values are 0 Sequence Models coursera-platform	2	488	May 16, 2023
Vote Week 1 Assignment 1 RNN_backward Exercise 6: wrong output data Sequence Models coursera-platform	13	685	December 18, 2024
C5W1A1 optional hw Sequence Models coursera-platform	10	1114	January 30, 2022
dWaa value of rnn_cell_backward Sequence Models coursera-platform	2	554	August 11, 2022

Trouble results delivered by rnn_backward

Related topics