Logistic Regression_Squared error W3

Course Q&A Machine Learning Specialization Supervised ML: Regression and Classification
1

image

Greetings,

Question 1:
Why 1/2 has been written inside the summation? as we kept on writing it outside, any specific reason? or is it just for simplicity in calculation?

Question 2:
What does “Loss function on a single training example” actually means here? as previously we did not name it as “loss” then why in logistic regression.

I`d be glad if you help me out in this concept
Regards.

1 Like
2

Hello @MUHAMMAD_USAMA_SHABB,

  1. It is just okay to write it inside or outside. When we calculate, we put it outside.

  2. Our convention is to call it “loss” when we consider one sample - no summation sign and no 1/m. We call it “cost” when we consider more than one sample together - with the summation sign and 1/m.

Cheers,
Raymond

1 Like
3

Thank you:) @rmwkwok

1 Like