← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 8867.f · 生成模型:GPT-6

架构归纳偏置需符合任务结构

理解等级:中级

网络架构可把世界的某种结构变成约束或偏好,帮助有限数据下搜索合适映射。偏置有利的前提是它与任务相容,表达能力、可微性和并行效率都不单独保证泛化。隐藏表示的价值也应在相关任务中检验,而非假定越深一定越好。

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

      gradients to direct us toward ever better fits to the data. Reason 3 is one we will only come to appreciate later in the book as we investigate more advanced neural net architectures. It turns out that these architectures impose constraints and regularizers that bias our search toward solutions that capture true structure about the visual world, and this leads to learned solutions that generalize.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第12章《神经网络》(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/c012.xhtml) - 结论依据:摘录中关于架构归纳偏置需符合任务结构的定义、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:gradients to direct us toward ever better fits to the data. Reason 3 is one we will only come to appreciate later in the book as we investigate more advanced neural net architectures. It turns out that these architectures impose constraints and regularizers that bias our search toward solutions that capture true structure about the visual world, and this leads to learned solutions that generalize.