← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6581.b · 生成模型:GPT-6

区组由双向边连通形成

理解等级:高级

含潜变量的观测图常用双向边表达隐藏混杂;district或c-component是双向边连通的极大节点集合。按这些集合分解有助于识别算法递归处理混杂,不能把它简单理解成任意具有共同祖先的节点集合。

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

      A c-component (confounded component) is a set of nodes in a DAG where each pair of observable nodes is connected by a path with edges that always point toward, never away from, the observable nodes (these are the “orphaned cousins” mentioned in chapter 4). The joint probability of the observed variables can be factorized into c-components, and this fact enabled step 2. Factorizing over c-components

    参考来源

    - 位置:《Causal AI》第10章《识别与因果层级》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-10.xhtml) - 结论依据:摘录中关于区组由双向边连通形成的定义、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:A c-component (confounded component) is a set of nodes in a DAG where each pair of observable nodes is connected by a path with edges that always point toward, never away from, the observable nodes (these are the “orphaned cousins” mentioned in chapter 4). The joint probability of the observed variables can be factorized into c-components, and this fact enabled step 2. Factorizing over c-components