We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
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
The text was updated successfully, but these errors were encountered:
No branches or pull requests
概要
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
The text was updated successfully, but these errors were encountered: