← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9102.c · 生成模型:GPT-6

构造更坏失败也能增加认识

理解等级:中级

若暂时无法让系统成功,可寻找让失败更稳定或更严重的条件,以暴露敏感因素。反例、退化输入与最小失败案例能帮助区分假设;必须说明它们支持了什么边界,不能把人为恶化结果当作自然场景总体表现。

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

      Please don't report to me and say, “This instance doesn't work.” Why doesn't it work? Why should it work? Is there a simpler case we can make work? Do you think it's a general issue that affects all problems of this category? Can you think of what's not working? Can you contort things to make an example that does work? At the very least, can

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第52章《如何做研究》(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/c052b.xhtml) - 结论依据:摘录中关于构造更坏失败也能增加认识的定义、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:Please don't report to me and say, “This instance doesn't work.” Why doesn't it work? Why should it work? Is there a simpler case we can make work? Do you think it's a general issue that affects all problems of this category? Can you think of what's not working? Can you contort things to make an example that does work? At the very least, can