← 返回卡片

原书出处

Reliable Machine Learning

03 Basic Introduction to Models

First Edition · 核验版本的摘录快照 · 导入于 2026-11-14T07:41:43.869Z

When deep learning methods are wrong, they might be very wrong Deep learning methods extrapolate from their training data, which means that the more unfamiliar a new previously unseen data point is, the more likely we are to have an extreme prediction that might be completely off base or out of the range of typical behavior. These sorts of highly confident errors can be a significant source of system-level misbehavior.

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/Reliable Machine Learning/_epub-src/OEBPS/ch03.xhtml

EPUB SHA-256:1201425671b4d9d06d56459bced6f75ec74a7aac380ea24f5b573c80fee7be65