原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
One way of formalizing this setting is to consider the teacher as a well-trained model t : X → Y that maps input queries to output answers. The student (the learner) observes both data and has access to the teacher model t. The student can learn to imitate the teacher's outputs or can learn to match how the teacher processes the queries, matching intermediate activations
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/c037.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8