← 返回卡片

原书出处

Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)

核验版本的摘录快照 · 导入于 2026-11-14T15:40:56.548Z

We define these vectors as linear transformations of the token's code vector, projecting to query/key/value vectors of length m. For a token t, we have: (26.11) (26.12) (26.13) Here is a question to think about: Could you use other differentiable functions to compute the query, value, and key? Would that be useful? In transformers, all inputs to the net are tokenized, so the textual question

此预览只包含定位所需的摘录和上下文。

原书定位详情

来源:a19c7933-4eda-4176-aebd-30fe7e1ad292

正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c026.xhtml

EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8