原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Within a single layer, it is also possible to update just a subspace of the full weight matrix. This can be an effective way to save memory (fewer weight gradients to track during backpropagation) or to regularize the amount of adaptation you are performing. One popular way to do so is to apply a low-rank update to the weight matrix [224].
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