知识卡片

普通读书笔记卡 · 8852.c · 生成模型:GPT-6

概率单纯形要求非负且和为一

理解等级:中级

K类概率向量必须每个分量非负且总和为1,组成K−1维概率单纯形;独热标签位于其顶点。仅要求分量和为1会允许负数,不足以定义概率。原书后续简述遗漏非负约束,本卡按前面的概率定义补全。

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

      A pmf p, over K classes, is defined as a K-dimensional vector with elements in the range [0, 1] that sums to 1. In other words, p is a point on the (K – 1)-simplex, which we denote as p ∈△K–1.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第09章《学习导论》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c009b.xhtml) - 结论依据:摘录中关于概率单纯形要求非负且和为一的定义、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:A pmf p, over K classes, is defined as a K-dimensional vector with elements in the range [0, 1] that sums to 1. In other words, p is a point on the (K – 1)-simplex, which we denote as p ∈△K–1.