← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6538 · 生成模型:GPT-6

概率推断改变查询分布

理解等级:初级

模型可能容易从P(Z,Y)联合采样,而实际问题需要给定Y后的P(Z|Y)。概率推断在模型假设下计算或近似目标分布,不必等同于学习模型参数;生成、参数学习和给定证据的推断需要分开描述。

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

      2.2.5 Programming probabilistic inference Suppose we implement in code a random process that generates an outcome {x, y, z} from P (X, Y, Z ) as follows: Further, suppose we are interested in generating from P (Z |Y = 3). How might we do this? Our process can sample from P (Z ), P (X |Z ), and P (Y |Z ), but it is

    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:摘录中关于概率推断改变查询分布的定义、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:2.2.5 Programming probabilistic inference Suppose we implement in code a random process that generates an outcome {x, y, z} from P (X, Y, Z ) as follows: Further, suppose we are interested in generating from P (Z |Y = 3). How might we do this? Our process can sample from P (Z ), P (X |Z ), and P (Y |Z ), but it is