知识卡片
变换模型与推断算法分工
先根据查询对因果模型做机制替换、节点拆分或多世界变换,再用概率推断求修改模型的目标分布。概率算法负责计算模型含义,不能判断这些因果假设是否真实,也不能把任意给定模型的答案变成已识别现实效应。
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
Given a causal generative model and a target causal query, we have two steps to infer the target query: first, apply the transformation, and then run probabilistic inference. We did this with the online gaming example at the end of chapter 10. We targeted P (IE= 0) and P (IE= 0 |E = 1). For each of these queries, we used the do function in
参考来源
- 位置:《Causal AI》第11章《构建因果推断工作流》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-11.xhtml)
- 结论依据:摘录中关于变换模型与推断算法分工的定义、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:Given a causal generative model and a target causal query, we have two steps to infer the target query: first, apply the transformation, and then run probabilistic inference. We did this with the online gaming example at the end of chapter 10. We targeted P (IE= 0) and P (IE= 0 |E = 1). For each of these queries, we used the do function in