原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
An important property of transformers is that they are equivariant to permutations of the input token sequence. This follows from the fact that both tokenwise layers, Fθ, and attention layers, attn, are permutation equivariant:
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