原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Another idea associated with transformers is positional encoding. Operations over tokens in a transformer are permutation equivariant, which means that we can shuffle the positions of the tokens and nothing substantial changes (the only change is that the outputs get permuted). A consequence is that tokens do not know encode their position within the representation of the signal.
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