mx-lsoftmax
mx-lsoftmax copied to clipboard
why we need minus w_y_i in the end?
i don't understand why we need minus w_y_i (or x_i) in the end of the formula. silly question------
take a look at the derivatives. here is the latex version
you remove y_i != j, so we should do it. Am I right?
Yes. The first item is the original fc derivatives.
I understand it. Thank you for your patience.
Does the definition of J equals the equation (4) in original paper?
I can't understand the derivation from 1 to 2 in your latex version.
I have wrote some definition of the relations about different variables.
Can you help me to point out what I have wrong. Thanks!