Skip to content
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.

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

Parameters a_j and b_j #3

Open
kwea123 opened this issue Jun 26, 2020 · 0 comments
Open

Parameters a_j and b_j #3

kwea123 opened this issue Jun 26, 2020 · 0 comments

Comments

@kwea123
Copy link

kwea123 commented Jun 26, 2020

As discussed in A.3, training a and b does not seem to influence the performance. An intuition is as what you mentioned: "as the b_j values do not deviate significantly from their initial values" (How about a_j?). Do you have any theoretic evidence of why this is true? To my knowledge, in language processing tasks, they let the network learn also the embedding of each token, and it makes the performance better.

Is there a notebook to experiment with this (Figure 8)?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant