原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
the region that is strictly positive occupies only proportion of the embedding space, so almost the entire space gets mapped to the axes after a relu layer. The geometry of high-dimensional neural representations may become very sparse because of this, where most of the volume of representational space is not occupied by any datapoints.
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/c013.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8