C1W4A1: Building your Deep Neural Network: Step by Step In the last exercise (no. 10) parameters["W" + str(l+1)] = parameters["W" + str(l+1)] - learning_rate * grads["dW" + str(l + 1)] parameters["b" + str(l+1)] = parameters["b" + str(l+1)] - learning_rate * grads["db" + str(l + 1)] passes both t…

[image] SRezaS: parameters = params.copy() That does not work, because parameters is a compound object. That creates a new copy of the whole dictionary, but the individual arrays in the dictionary are not duplicated. You need the deepcopy as I see you discovered in your later post on this thr…

Clarification on the reason of failed excesrise

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

paulinpaloalto September 2, 2023, 5:42pm 8

Please read this thread to understand why that is. You need “copy” or “deepcopy” to break the connection to the global variables.

Topic		Replies	Views
Use "-=" gives wrong result and does not pass the test Neural Networks and Deep Learning	6	746	August 19, 2021
Week 4 Building Neural Network Neural Networks and Deep Learning	4	622	July 20, 2021
W4_A1_subtlety in updating parameters Neural Networks and Deep Learning	1	590	January 8, 2023
Week 4 - Assignment1 - Exercise 10 / Update parameters Neural Networks and Deep Learning	2	644	June 15, 2021
Week 4 Excercise 10 Programming Assignment # 1 Neural Networks and Deep Learning	4	1150	October 7, 2022

Clarification on the reason of failed excesrise

Related topics