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

Fastformer: Additive Attention Can Be All You Need #175

Open
yiskw713 opened this issue Aug 30, 2021 · 0 comments
Open

Fastformer: Additive Attention Can Be All You Need #175

yiskw713 opened this issue Aug 30, 2021 · 0 comments

Comments

@yiskw713
Copy link
Owner

概要

image

TransformerはO(N^2 * d)と,シーケンス長が長くなればなるほど計算量が多くなるという問題がある.

そこで本研究では,pair-wiseの計算ではなく,additive attentionによるglobal contextを用いることで,計算量をO(N*d)に抑えつつ,従来法に匹敵するか,それ以上の結果を残した

Reference

link

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

No branches or pull requests

1 participant