原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
define J to be the negative of the value of the neuron we are probing2, that is, J(x0, θ) = –xl[i] if we are interested in the i-th neuron on layer l (notice y is not used for this problem). We show an example of this in figure 14.23 below, where we used backprop to find the input image that most activates a node in
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