← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8998 · 生成模型:GPT-6

潜变量解释依赖观察范围

理解等级:中级

单帧球的位置与颜色可见,而速度方向可能不确定,因此速度是解释下一帧差异的一种潜因素。但颜色不变、速度有界等仍是该例的动力学假设,网络也不保证将某个z坐标学成真实速度。潜表示可解释性需要额外检验。

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

      The idea is that z should only encode bits of information about y that are independent from whatever x already tells us about y. For example, suppose that we are trying to predict the motion of a billiard ball bouncing around in a video sequence. We are given a single frame x and asked to predict the next frame y. Only knowing x we can't

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第34章《条件生成模型》(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/c034.xhtml) - 结论依据:摘录中关于潜变量解释依赖观察范围的定义、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:The idea is that z should only encode bits of information about y that are independent from whatever x already tells us about y. For example, suppose that we are trying to predict the motion of a billiard ball bouncing around in a video sequence. We are given a single frame x and asked to predict the next frame y. Only knowing x we can't