← 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 2026-11-14T15:40:56.563Z

This step is known as the reparameterization trick, as it reparameterizes a stochastic function (sampling from a Gaussian parameterized by a neural net) to be a deterministic transformation of a fixed noise source (the unit Gaussian). To optimize the parameters for the encoder, we only need to backprogate through μz and σz, which are deterministic functions of x, and therefore we have sidestepped the need

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/c033.xhtml

EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8