← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8861.b · 生成模型:GPT-6

查表式记忆展示拟合的不足

理解等级:中级

星号例既可由简短代数规则解释,也可由逐条判断已见输入、其他输入返回固定值的程序拟合。两者训练误差都可为零,对新输入却不同。图中所谓Python程序使用&&,不能直接运行;这里保留查表机制,而不把伪代码当已验证实现。

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

      That also perfectly fits the observed data. Why didn't you come up with those answers? What made x ⋆ y = (xy)2 more compelling? We suspect your reason is again Occam's razor, which states that when multiple hypotheses equally well fit the data, you should prefer the simplest. To a human, it may be that x ⋆ y = (xy)2 is the simplest. To a

    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:摘录中关于查表式记忆展示拟合的不足的定义、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:That also perfectly fits the observed data. Why didn't you come up with those answers? What made x ⋆ y = (xy)2 more compelling? We suspect your reason is again Occam's razor, which states that when multiple hypotheses equally well fit the data, you should prefer the simplest. To a human, it may be that x ⋆ y = (xy)2 is the simplest. To a