知识卡片
有向分解需要无环结构
贝叶斯网络在有向无环图上写成∏i p(xi|父节点),每个条件分布均需归一化,根节点提供先验。任意带环有向图的条件概率乘积并不自动构成这样的联合分布。有向边可用于因果模型,但仅有统计分解不保证具备干预语义。
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
- · 概率图模型
原书出处 · 1 处
- · 查看原书依据
The general rule for writing the joint probability described by a directed graph is this: Each node, xn, contributes the factor p(xn | xΞ), where Ξ is the set of nodes with arrows pointing in to node xn. You can verify that equation (29.5) follows this rule. Directed graphical models are often used to describe causal processes.
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第29章《概率图模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c029.xhtml)
- 结论依据:摘录中关于有向分解需要无环结构的定义、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:The general rule for writing the joint probability described by a directed graph is this: Each node, xn, contributes the factor p(xn | xΞ), where Ξ is the set of nodes with arrows pointing in to node xn. You can verify that equation (29.5) follows this rule. Directed graphical models are often used to describe causal processes.