New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Technique mistake in the paper #2

Closed

hangg7 opened this issue May 21, 2018 · 1 comment

hangg7 commented May 21, 2018

Hi,

About computing p(x|T), the technique currently listed in the paper is wrong:

It's clear that you are trying to normalize all scores in a batch using softmax where score function is the sum over masked activations, i.e.,

however the trace operation is not correct, since it would end in

Please consider the modification - it might be a minor mistake however resulting in unnecessary confusion.

xizero00 commented Dec 3, 2018

Hi
@cullengao , I also find this typo.

hangg7 closed this as completed

colorfuldarkgray mentioned this issue

Flipping of masks in the batch and filter dimension #8

Open

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment