知识卡片

普通读书笔记卡 · 6555.e · 生成模型:GPT-6

板记号压缩重复结构

理解等级:中级

板记号用框表示重复的变量或子图,标注次数与索引;嵌套框可分别表达N个样本和每图784个像素。它压缩表示但仍带建模假设,尤其不要把图形中的重复自动等同于真实数据已满足无条件独立。

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

      Plate modeling is a visualizing technique used in probabilistic machine learning that provides an excellent way to visualize the higher-level abstractions while preserving the lower-level dimensional detail. Plate notation is a method of visually representing variables that repeat in a DAG (e.g., X1 to X16 in figure 5.4)—in our case, we have repetition of the pixels.

    参考来源

    - 位置:《Causal AI》第05章《连接因果与深度学习》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-5.xhtml) - 结论依据:摘录中关于板记号压缩重复结构的定义、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:Plate modeling is a visualizing technique used in probabilistic machine learning that provides an excellent way to visualize the higher-level abstractions while preserving the lower-level dimensional detail. Plate notation is a method of visually representing variables that repeat in a DAG (e.g., X1 to X16 in figure 5.4)—in our case, we have repetition of the pixels.