Course 1, Week 3, Exercise 5

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

Hi mentor. I’m difficult to use np.dot instead of using np.multiply. I want to try it.
I wrote cost statement as follows:

Compute the cross-entropy cost

# (≈ 2 lines of code)
# logprobs = ...
# cost = ...
# YOUR CODE STARTS HERE

#logprobs = np.multiply(np.log(A2),Y) + np.multiply(np.log(1-A2), 1-Y)
#cost = (-1/m)*np.sum(logprobs)  
cost = (-1/m) * np.sum(np.dot(Y, np.log(A2)) + np.dot(1-Y, log(1-A2)))
# YOUR CODE ENDS HERE

Please help me. Thanh you very much.

2

That will throw an error (as I’m sure you discovered). The problem is that the dimensions don’t work for dot products without a transpose. Please see this thread for some examples.