知识卡片

普通读书笔记卡 · 6531.b · 生成模型:GPT-6

参数必须满足分布约束

理解等级:初级

一个三类别分布可以用ρ1、ρ2表示前两项,第三项为1−ρ1−ρ2,但必须满足ρ1≥0、ρ2≥0且ρ1+ρ2≤1。参数减少不等于可以任意取值;类别数等结构设定也与可自由优化的数值参数不同。

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

      Figure 2.9 Adding parameters to the data structure The reason the third probability value is a function of the other two (instead of a third argument, ρ3) is because the probability values must sum to one. The set of two values {ρ1, ρ2} are the parameters of the distribution. In programming terms, I could create a data type that represents a table with three values.

    参考来源

    - 位置:《Causal AI》第02章《概率生成建模入门》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-2.xhtml) - 结论依据:摘录中关于参数必须满足分布约束的定义、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:Figure 2.9 Adding parameters to the data structure The reason the third probability value is a function of the other two (instead of a third argument, ρ3) is because the probability values must sum to one. The set of two values {ρ1, ρ2} are the parameters of the distribution. In programming terms, I could create a data type that represents a table with three values.