I have a trouble merging lstm_cell_backward in lstm_backward because the former requires dc_next but the latter exercise(lstm_backward) does not provide it. Maybe I have missed something. Please advise me. Thanks, Youngha

[image] Youngha_Hwang: da_prev = np.dot(parameters['Wf'].T, dft) + np.dot(parameters['Wi'].T, dit) + np.dot(parameters['Wc'].T, dcct) + np.dot(parameters['Wo'].T, dot) is not correct. [Screen Shot 2021-11-18 at 13.12.20]

C5W1 A1 (Ex8) lstm_backward, dc_next missing?

Course Q&A Deep Learning Specialization Sequence Models

saifkhanengr May 4, 2023, 5:00am 15

I’ve replied to your original post. Kindly check it here.

Best,
Saif.

1 Like

Topic		Replies	Views
Course 5 Week 1 Assignment 1 Where is dc_next for lstm_backwards Sequence Models coursera-platform	4	645	October 18, 2021
Help needed in Building your RNN Step by Step Sequence Models coursera-platform	4	652	May 26, 2021
C5W1 - Assignment 1 - Optional Part - lstm_backward - missing parameter Sequence Models coursera-platform	5	696	December 7, 2023
[C5W1A1] wrong results of lstm_backward Sequence Models coursera-platform	14	1354	August 2, 2024
Seq models wk1 assign1 lstm_backward output mismatch Sequence Models coursera-platform	1	726	October 29, 2021

C5W1 A1 (Ex8) lstm_backward, dc_next missing?

Related topics