← 返回起始笔记位置

知识卡片

结构图卡 · 8853.b · 生成模型:GPT-6

学习与元学习的两层输出

理解等级:中级

内层产生可用于预测的函数,外层产生或调整能从任务数据学习的学习器。区分每层输入、输出和未见对象,才能设计正确评估。

结构图:

flowchart LR
 A[多个训练任务] --> B[外层学习过程]
 B --> C[学习器及其超参数]
 C --> D[内层任务训练]
 E[新任务训练数据] --> D
 D --> F[任务预测函数]
 F --> G[新任务测试输入的输出]
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

      We started this chapter by saying the learning is a meta-algorithm: it's an algorithm that outputs an algorithm. Metalearning is a meta-meta-algorithm and we can visualize it by just adding another outer loop on top of a learner, as shown in figure 9.10.

    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:摘录中关于学习与元学习的两层输出的定义、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:We started this chapter by saying the learning is a meta-algorithm: it's an algorithm that outputs an algorithm. Metalearning is a meta-meta-algorithm and we can visualize it by just adding another outer loop on top of a learner, as shown in figure 9.10.