原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
things about this forward-backward network. One is that activations from the relu layers get transformed to become parameters of a linear layer of the backward network (see equation (14.33)). There is a general term for this setup, where one neural net outputs values that parameterize another neural net; this is called a hypernetwork [179]. The forward network is a hypernetwork that parameterizes the backward network.
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/c014.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8