← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9170.c · 生成模型:GPT-6

独热编码表示类别而非顺序

理解等级:中级

K个类别用长度K向量、真实类位置为1其余为0表示,避免把类别编号当连续距离。它可作为单样本退化目标分布,不等于数据总体类别频率,更不表示类别之间存在数值大小关系。

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 very common approach is known as one-hot encoding (OHE). In OHE, n discrete labels such as numbers or characters are encoded as a binary vector of length n. To encode the i−th element of a set of labels, this vector is 0 except at position i. For example, to encode the characters 0…9, OHE would represent them as follows:

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第10章《人工神经网络》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)/_epub-src/OEBPS/xhtml/chapter_10.xhtml) - 结论依据:摘录中关于独热编码表示类别而非顺序的定义、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 very common approach is known as one-hot encoding (OHE). In OHE, n discrete labels such as numbers or characters are encoded as a binary vector of length n. To encode the i−th element of a set of labels, this vector is 0 except at position i. For example, to encode the characters 0…9, OHE would represent them as follows: