Hi, I get all right results until exercise 5 , my cost function is computed as

cost = - (np.dot(Y,np.log(A).T)+np.dot((1-Y),np.log(1-A).T))/m

but then for exercice 6 I get AssertionError: Wrong values for costs. [array(5.80154532), array(0.58923175)] != [5.80154532, 0.31057104]

What did I do wrong?

Itβs close. You see the error in updating b. It must be βdbβ, not βbβ.

By the way, posting your code in here is not recommended. We start with Trackback.

So, please remove them

By the way, learning_rate is a scaler. So, you may not be necessary to use np.dot to update w.

1 Like