Week 2: propagate function error

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

def propagate(w, b, X, Y):
m = X.shape[1]

A = sigmoid(np.dot(w.T, X) + b)
cost = np.sum((( - np.log(A)) * Y + (-np.log(1 - A))*(1 - Y)) / (m)

dw = np.dot(X, (A-Y).T) / m
db = np.sum(A-Y)/ m

cost = np.squeeze(np.array(cost))


grads = {"dw": dw,
         "db": db}

return grads, cost

output error →
File “”, line 42
dw = np.dot(X, (A-Y).T) / m
^
SyntaxError: invalid syntax

2

Check the brackets in the line upwards, cost, they dont match!

3

Sometimes it is confusing to me when to use matrix multiplication and when to use elementwise multiplication. I was using matrix multiplication to calculate the cost and I was getting inaccurate answers. I will reflect on my understanding. I know the difference is subtle :smiley:

4

Can you please specify for which codes line your question pertains to?

you can mention in your comment if the code is not part of any grader cell.

Regards
DP