Variational-NMT icon indicating copy to clipboard operation
Variational-NMT copied to clipboard

Published 20 hours ago • verified publisher icon wang-h

KL loss function

Open SZH1230456 opened this issue 4 years ago • 0 comments

Hello, I am confused about the KL loss function in the training process. In your paper VRNMT, you have mentioned that the z_j is integrated into the decoder network, did you mean the z_j in decoder derives from the prior network? Which makes me very confused. Look forward to your early reply.

SZH1230456 avatar Jun 28 '20 11:06 SZH1230456