← 返回卡片

原书出处

Causal AI

核验版本的摘录快照 · 导入于 2026-11-14T08:43:24.515Z

Suppose then you fed the trained model data actual samples of three-sided die rolls, with the goal of predicting the ground-truth SCM. That predictive model’s prediction might favor a stick with the {1, 2, 3} ordering over the equivalent {2, 3, 1} ordering. But it would only do so if the {1, 2, 3} ordering was more common in the training data.

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/Causal AI/_epub-src/OEBPS/Text/chapter-6.xhtml

EPUB SHA-256:e55e7dc9d7966ea79311f2bc8d5bef7371a6dbb65240f11a2b3e44180b934e72