← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8824 · 生成模型:GPT-6

Marr分层区分任务算法实现

理解等级:中级

Marr主张分别描述要计算什么及为什么、采用何种表示与算法、以及如何在物理硬件实现。任务映射不等于某个网络架构,算法可依赖表示而不被某种器件唯一限定。选择恰当层次,有助避免用实现细节替代对目标的解释。

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

      Computational theory. This level of description should answer the following questions: what is the task to be perform and why should it be carried out? In the case of vision, the task is to derive properties of the world from images. This level of description should specify what the mapping is between the input and output, and why this mapping is appropriate for the task

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第01章《视觉的挑战》(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/c001.xhtml) - 结论依据:摘录中关于Marr分层区分任务算法实现的定义、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:Computational theory. This level of description should answer the following questions: what is the task to be perform and why should it be carried out? In the case of vision, the task is to derive properties of the world from images. This level of description should specify what the mapping is between the input and output, and why this mapping is appropriate for the task