Week 1 Programming Assignment-3 Gradient Checking Exercise-4

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

Hi, I am facing an issue with the backpropagation. the difference is coming 1.0 which is not expected. I am not sure what I am doing wrong? I also try to fix the error in backpropagtion but nothing is reflecting on the output. Please help!

There is a mistake in the backward propagation! difference = 1.0

AssertionError Traceback (most recent call last)
in
6 expected_values = [0.2850931567761623, 1.1890913024229996e-07]
7 assert not(type(difference) == np.ndarray), “You are not using np.linalg.norm for numerator or denominator”
----> 8 assert np.any(np.isclose(difference, expected_values)), “Wrong value. It is not one of the expected values”

AssertionError: Wrong value. It is not one of the expected values

2

Please message your notebook to me. (click on my name and then on Message to send it as an attachment).

3

Thanks balaji.ambresh, It is resolved.

4

You’re welcome, @Arti_Negi. To share context to the rest of the readers, when you code theta_minus, keep the sign of the operation in mind wrt theta_plus i.e. you have to subtract.

5

Oh Geez, Duh. Subtract epsilon for theta_minus.

Thanks.