← 返回卡片

原书出处

Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)

核验版本的摘录快照 · 导入于 2026-11-14T15:40:56.527Z

relu layer maps many points to the axes of the positive quadrant. In general, with relu-nets, a lot of data density will build up along these axes, because any point not in the positive quadrant snaps to an axis. This effect becomes exaggerated in real networks with high-dimensional embeddings. In particular, for a width-N layer, the region that is strictly positive occupies only proportion of

此预览只包含定位所需的摘录和上下文。

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