知识卡片

普通读书笔记卡 · 9084.a · 生成模型:GPT-6

原型刻画典型性而非硬边界

理解等级:中级

自然类别常有模糊边界,原型强调典型成员与相似程度,可补充非黑即白的分类思路。原型假说不意味着所有类别都可由一个平均样本完整定义,也不自动解决不同语境下的用途变化。

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

      However, as argued by E. Rosch [411], “natural categories tend to be fuzzy at their boundaries and inconsistent in the status of their constituent members.” Rosch suggested that categories can be represented by prototypes. Prototypes are the clearest members of a category. Rosch hypothesized that humans recognize categories by measuring the similarity to prototypes. By using prototypes, Rosch [411] suggested that it is easier to

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第50章《目标识别》(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/c050b.xhtml) - 结论依据:摘录中关于原型刻画典型性而非硬边界的定义、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:However, as argued by E. Rosch [411], “natural categories tend to be fuzzy at their boundaries and inconsistent in the status of their constituent members.” Rosch suggested that categories can be represented by prototypes. Prototypes are the clearest members of a category. Rosch hypothesized that humans recognize categories by measuring the similarity to prototypes. By using prototypes, Rosch [411] suggested that it is easier to