Translations:Attention Mechanisms/17/zh

    From Marovi AI
    Revision as of 03:21, 27 April 2026 by DeployBot (talk | contribs) (Batch translate Attention Mechanisms unit 17 → zh)
    (diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

    缩放因子 $ \sqrt{d_k} $ 防止点积随着键维度 $ d_k $ 的增加而变得过大,否则会使 softmax 进入梯度极小的区域。