← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6578.c · 生成模型:GPT-6

层级定理约束可用信息

理解等级:高级

低层分布一般不能单独确定高层目标,必须说明补充的机制或识别假设。这个一般性限制不能改写成每一个高层查询均不可识别;某些目标可借图条件、特殊结构或代数化简由较低层信息求出。

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

      almost always separate.” Roughly speaking, “separate” means that data from a lower level of the hierarchy is insufficient to infer a query from a higher level of the hierarchy. And “almost always” means this statement is true except in cases so rare that we can dismiss them as practically unimportant.

    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:摘录中关于层级定理约束可用信息的定义、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:almost always separate.” Roughly speaking, “separate” means that data from a lower level of the hierarchy is insufficient to infer a query from a higher level of the hierarchy. And “almost always” means this statement is true except in cases so rare that we can dismiss them as practically unimportant.