[Screenshot 2023-10-27 134627] I’ve been trying to fix this…but I’m stuck.

When you do a dot product between two vectors or matrices, the order matters. Matrix multiplication is not a commutative operation in general. In this case you’ve got two vectors of dimension 1 x m. You did Y^T \cdot log(A), so that is m x 1 dotted with 1 x m, so you get an m x m output, right? But …

You have to transpose one term in cost.

The error changes to this… [one]

And when I remove the transpose in dw, I get this… [two] At this point, I don’t understand what I’m doing. I’m just trying to make the error go away by trial and error. Please help me to understand

Using * (multiply) is not the same as np.dot.

Also note that once you fix this you’ll probably have some other issues to deal with. Maybe you have already fixed it, but the code you show for the cost above is incomplete even after you fix the transpose issue. If you get the wrong cost value, please compare your code to the math formula for the …

I changed my cost function and the error has been this… [ex5_error]

When I used the dot product, I had wrong values

Thank you for sending me your code. As Paul and I mentioned earlier, using * is not the same as using np.dot. Please read the thread Paul has linked for you and avoid making the same mistake again.

C1_W2_Programming_assignment (logistic regression with a neural network mindset)

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

paulinpaloalto October 27, 2023, 3:48pm 6

Right! Please see this thread for more about when to use * and when to use np.dot.

Topic		Replies	Views
Cost function in Week 2 Exercise 5 Neural Networks and Deep Learning coursera-platform	6	713	July 9, 2023
Course 1, Week 3, Exercise 5 Neural Networks and Deep Learning coursera-platform	1	616	August 27, 2021
W4_A1_Ex-6_cost function with python programming Neural Networks and Deep Learning coursera-platform	3	653	January 6, 2023
Course 1 Week 2 Logistic Regression Cost function Neural Networks and Deep Learning coursera-platform	4	766	September 28, 2021
When to use np.dot Neural Networks and Deep Learning coursera-platform	11	1470	January 29, 2023

C1_W2_Programming_assignment (logistic regression with a neural network mindset)

Related topics