《动手学深度学习》中的多层感知机

隐藏层

多层感知机含有一个隐藏层，

该模型包含单个隐藏层的多层感知机设计方案及其输出结果的公式如下所示。

\begin{aligned} \boldsymbol{H} &= \boldsymbol{X} \boldsymbol{W}_h + \boldsymbol{b}_h,\\ \boldsymbol{O} &= \boldsymbol{H} \boldsymbol{W}_o + \boldsymbol{b}_o, \end{aligned}

将以上两个式子联立起来，可以得到

该 computation results in O being equal to the sum of two terms: first, the product of X, Wh, and Wo; second, the sum of bh multiplied by Wo and bo. This computation results in O being equal to the sum of two terms: first, the product of X, Wh, and Wo; second, the sum of bh multiplied by Wo and bo.

尽管神经网络增添了一个隐藏层序列却仍等价于一个单层神经网络：其中输出权重由所有隐藏至输出的乘积