知识卡片

普通读书笔记卡 · 9173.e · 生成模型:GPT-6

池化图示尺寸要服从明确规则

理解等级:中级

7×7输入、3×3窗口、步长1且不补边时输出应为5×5,步长3则为2×2。图10.11标为6×6和3×3却未给对应补边或ceil规则,不能将其标注直接当通用尺寸公式。

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

      Figure 10.11 Pooling using a pool size of 3 × 3 for different strides and corresponding output. Although the max() function is not differentiable, MaxPooling can still be used in backpropagation by selectively passing the gradient to only the neuron that has shown to have the maximum activation and setting the gradient of all other neurons to zero. When an averaging pooling function is used, the

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第10章《人工神经网络》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)/_epub-src/OEBPS/xhtml/chapter_10.xhtml) - 结论依据:摘录中关于池化图示尺寸要服从明确规则的定义、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:Figure 10.11 Pooling using a pool size of 3 × 3 for different strides and corresponding output. Although the max() function is not differentiable, MaxPooling can still be used in backpropagation by selectively passing the gradient to only the neuron that has shown to have the maximum activation and setting the gradient of all other neurons to zero. When an averaging pooling function is used, the