知识卡片
可逆完整观测允许确定溯因
若观察足够完整,且相关结构函数对外生输入在相应支持上可逆,可以从事实逆解外生值,再计算替代结果。缺失观测、多解或不可逆机制时仍需保留分布;“所有变量已观测”本身不保证每个噪声可唯一恢复。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
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
Deterministic abduction A special case of the abduction step is when both of the following are true: You observe all the endogenous variables. The SCM assignment functions are invertible. In that case, given observations of all the endogenous variables, you can calculate exact point values for the exogenous variables with the inverted assignment functions. Consequently, you apply the assignment functions in the hypothetical world to
参考来源
- 位置:《Causal AI》第09章《通用反事实推断算法》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-9.xhtml)
- 结论依据:摘录中关于可逆完整观测允许确定溯因的定义、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:Deterministic abduction A special case of the abduction step is when both of the following are true: You observe all the endogenous variables. The SCM assignment functions are invertible. In that case, given observations of all the endogenous variables, you can calculate exact point values for the exogenous variables with the inverted assignment functions. Consequently, you apply the assignment functions in the hypothetical world to