1
$\begingroup$

I'm trying to implement drop connect. Am I supposed to use the same drop masks during back propagation?

$\endgroup$
1
$\begingroup$

Yes, because back propagation is for computing gradients.

If some connection is blocked by the mask, it contributes nothing to the loss, so its associated gradient should be zero.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.