登録して招待リンクを共有すると、動画再生報酬と紹介報酬を獲得できます。

wh
@nrehiew_
eng primarily, ml mostly, research previously
参加 October 2023
104 フォロー中    18.5K ファン
Next big section is on residuals which has devolved to something extremely extremely cursed. They first compare HyperConnections (learnable write, read, mix operators) against a simplied variant where its just a linear combination of various branches and the output is written to a single branch in a roundrobin fashion. They compare both of these with their own variant GatedResidual: 1) RMSNorm each branch 2) Apply projection via a low rank bottleneck 3) Layer is the input coefficients of the different branches 4) Write uses a single branch level scalar
もっと見る