← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 8866.b · 生成模型:GPT-6

逐点激活的范围与梯度不同

理解等级:中级

sigmoid将实数压到(0,1),tanh压到(−1,1),二者大幅值区间会饱和;ReLU正区间线性,leaky-ReLU为负区间保留斜率。具体斜率和零点规则属于模型定义。图中leaky-ReLU的参数标注与绘图不一致,不能只按示意图复制数值。

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

      linear functions. This is because the composition of N linear functions is a linear function. Activation layers add nonlinearity. Activation layers are typically pointwise functions, applying a scalar to scalar mapping on each dimension of the input vector. Typically parameters of these layers, if any, are not learned (but they can be). Some common activation layers are defined below and are plotted in figure 12.16:

    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:摘录中关于逐点激活的范围与梯度不同的定义、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:linear functions. This is because the composition of N linear functions is a linear function. Activation layers add nonlinearity. Activation layers are typically pointwise functions, applying a scalar to scalar mapping on each dimension of the input vector. Typically parameters of these layers, if any, are not learned (but they can be). Some common activation layers are defined below and are plotted in figure 12.16: