Problem with pragrmming assignment: logistic regression

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

Hi All,
I have been trying to intialize the w and b parameters to zero. I created the function which mandates the b to a float value, but it gives me asertionError when I am creating the b matrix. Please can some help me?
Thanks.

2

Hi @ericasare1 ,

If you set b=0.0 in initialize_with_zeros(), then the datatype for b should be a float.
What sort of assertionError did you have when creating the b matrix?

1 Like
3

Thanks Kim. I did it as you advised. It worked.

4

Right! The point in this case (which is unique to Logistic Regression) is that the bias value here is a scalar and not an array or vector. Pretty soon when we graduate to real Neural Networks, the bias values will be vectors.