← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6525.j · 生成模型:GPT-6

反事实记号不能替代识别推导

理解等级:高级

因果目标可用干预或反事实记号定义,再尝试转成可从观测分布估计的表达式。符号转换是否成立取决于图与假设;本章图像条件量涉及干预后变量,且示例权重公式缺少明确归一化,不作为通用调整公式采用,后续以识别章节为准。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      left side of this equation defines the expectations used in the CATE definition in the second step—it is a theoretical construct that captures the hypothetical condition “if writer type were set to ‘w’”. But the right side is actionable; it is composed entirely of terms we could estimate using machine learning methods on a hypothetical version of NIST image data labeled with the writers’ ages.

    参考来源

    - 位置:《Causal AI》第01章《为何需要因果AI》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-1.xhtml) - 结论依据:摘录中关于反事实记号不能替代识别推导的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:left side of this equation defines the expectations used in the CATE definition in the second step—it is a theoretical construct that captures the hypothetical condition “if writer type were set to ‘w’”. But the right side is actionable; it is composed entirely of terms we could estimate using machine learning methods on a hypothetical version of NIST image data labeled with the writers’ ages.