Gradient Check Exercise 3 : Mistake in Backward Propagation

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
1

In the gradient checking assignment on week 1, exercise 3 is printing “There is a mistake in the backward propagation! difference = 0.6000000001868375”. There are no errors and the forward prop and backward prop exercises previous passed their tests. I cannot understand why this is not working. I tried following the instructions as seen in my code.

{moderator edit - solution code removed}

Thanks guys
IC

2

Your computation of J_plus and J_minus is wrong. For starters, where is J on the RHS of those expressions defined? But that’s not the correct formula in any case, right? You just got done writing the forward_propagation function, which is what you should be using at that stage.