← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6554 · 生成模型:GPT-6

发现算法利用不同信息约束

理解等级:中级

约束式发现从独立性关系限制候选图,评分式发现比较候选图对数据的拟合与复杂度,函数式方法还假定机制形式。不同路线依赖不同前提;无论输出多清楚,都应记录用到的信息与不能区分的候选。

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

      constraint-based algorithms) do what I just suggested—reverse engineer a graph from evidence of conditional independence in the data. Other algorithms (often called score-based algorithms) turn the causal DAG into an explanatory model of the data and find causal DAGs that have a high goodness-of-fit score. Yet another approach is to assume additional constraints on the functional relationships between parents and children in the causal DAG,

    参考来源

    - 位置:《Causal AI》第04章《用因果约束检验DAG》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-4.xhtml) - 结论依据:摘录中关于发现算法利用不同信息约束的定义、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:constraint-based algorithms) do what I just suggested—reverse engineer a graph from evidence of conditional independence in the data. Other algorithms (often called score-based algorithms) turn the causal DAG into an explanatory model of the data and find causal DAGs that have a high goodness-of-fit score. Yet another approach is to assume additional constraints on the functional relationships between parents and children in the causal DAG,