Why use "CAddTable" instead of concatenating features in the memory network?
ruizhaogit opened this issue · comments
ruizhaogit commented
Hi Visdial Team,
I have a question regarding to combining the history and question features in the memory network encoder. Why do you use element add instead of simply concatenating like you did in the late fusion encoder? Is there any advantages in this?
Thank you in advance!
Best,
Rui
Abhishek Das commented
To be as close to the Memory Networks paper as possible. We haven't tried concatenating. Let us know how things go if you do :)
ruizhaogit commented
Alright :)