← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8861.e · 生成模型:GPT-6

假设空间是不能越过的边界

理解等级:中级

固定假设空间限定学习器能够输出的函数。缩小空间可降低搜索难度,但若把真实关系排除,增加样本或调整软先验也不能在该空间内精确恢复它。零函数空间搜索虽最简单,却无法表示非零直线;效率应与表达充分性一起考虑。

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

      If the true solution is not in our hypothesis space, then no amount of data or priors can help us find it. This situation is like the old joke of a drunk man looking for his lost keys under a lamppost [137]. “Why are you looking there,” a cop asks. “Because this is where the light is.”

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第11章《泛化问题》(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/c011.xhtml) - 结论依据:摘录中关于假设空间是不能越过的边界的定义、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:If the true solution is not in our hypothesis space, then no amount of data or priors can help us find it. This situation is like the old joke of a drunk man looking for his lost keys under a lamppost [137]. “Why are you looking there,” a cop asks. “Because this is where the light is.”