← 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 2026-11-14T15:40:56.521Z

This representation is called a one-hot code, since just one element of the vector is on (“hot”). Each class has a unique one-hot code. We will see why this representation makes sense shortly. The one-hot codes are the targets for the function we are learning. Our goal is to learn a function fθ that output vectors ŷ that match the one-hot codes, thereby correctly classifying

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/c009b.xhtml

EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8