Understanding backprop for softmax
1
$begingroup$
I'm looking on a given solution of the first assignment of cs231n course. Down below a snippet from the loss function. I don't really understand lines 140-143 . Can you explain why dscores (the derivative of scores ) is calculated like that?
neural-network deep-learning backpropagation cs231n
share | improve this question
asked Dec 22 '18 at 17:18
yaseco yaseco
106 1
$endgroup$
bumped to the homepage by Commun...