知识卡片

普通读书笔记卡 · 8852 · 生成模型:GPT-6

程序归纳扩大候选也扩大搜索

理解等级:中级

程序归纳可以在有长度约束的Python程序集合中搜索输入到输出的映射,比寻找两个回归参数宽泛得多,也更难搜索。能拟合样本的程序不一定泛化,更不保证任意输入均终止或正确;更强的候选集合需要额外约束与验证。

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

      At the other end of the spectrum we have what is known as program induction, which is one of the broadest classes of learning algorithm. In this setting, our hypothesis space may be all Python programs. Let's contrast linear least-squares with Python program induction. Figure 9.6 shows what linear least-squares looks like.

    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:摘录中关于程序归纳扩大候选也扩大搜索的定义、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:At the other end of the spectrum we have what is known as program induction, which is one of the broadest classes of learning algorithm. In this setting, our hypothesis space may be all Python programs. Let's contrast linear least-squares with Python program induction. Figure 9.6 shows what linear least-squares looks like.