导读:原文.在机器学习视频反向传播章节[1]中:.我们用 \(\delta\) 来表示误差,则: \(\boldsymbol\delta^{\left(4\right)}=\boldsymbol.a^{\left(4\right)}−\boldsymbol y\) 。我们利用这个误差值
在机器学习视频反向传播章节[1]中:
我们用 \(\delta\) 来表示误差,则: \(\boldsymbol\delta^{\left(4\right)}=\boldsymbol a^{\left(4\right)}−\boldsymbol y\) 。我们利用这个误差值来计算前一层的误差:
\(\boldsymbol\delta^{\left(3\right)}=\left(\boldsymbol\Theta^{\left(3\right)}\right)^T\boldsymbol\delta^{\left(4\right)}\cdot g^\prime\left(\boldsymbol z^{\left(3\right)}\right)\) 。其中 \(g^\prime\left(\boldsymbol{z}^{\left(3\right)}\right)\) 是 \(S\) 形函数的导数,
\(g^\prime\left(\boldsymbol z^{\left(3\right)}\right)=\boldsymbol a^{\left(3\right)}\cdot\left(1−\boldsymbol a^{\left(3\right)}\right)\) 。而 \(\left(\boldsymbol\Theta^{\left(3\right)}\right)^T\boldsymbol\delta^{\left(4\right)}\) 则是权重导致的误差的和。
\[\boldsymbol\delta^{\left(3\right)}=\left(\boldsymbol\Theta^{\left(3\right)}\right)^T\boldsymbol\delta^{\left(4\right)}\cdot g^\prime\left(\boldsymbol z^{\left(3\right)}\right) \]
看到这道算式时我百思不得其解。为什么凭空会有转置?
在我自己推一遍之后,发现原公式中可能有些不严谨的地方,所以在此阐述我的理解,欢迎大家指正:
对数似然代价函数: \(J\left(\Theta\right)=y\ln h\Theta\left(x\right)+\left(1-y\right)\ln\left(1-h\Theta\left(x\right)\right)\)
估计函数: \(h_\Theta\left(x\right)=\sum_i\Theta_ix_i= \begin{bmatrix}\Theta_1&\Theta_2&\cdots&\Theta_n\end{bmatrix} \begin{bmatrix}x_1\\x_2\\\vdots\\x_n\end{bmatrix}\)
Logistic
激活函数: \(g\left(x\right)=\frac1{1+{\rm e}^{-x}}\)
此外激活函数导数为: \(g^\prime\left(x\right)=g\left(x\right)\left[1-g\left(x\right)\right]\)
flowchart LR x1–“(Θ1(1))1”–>z12 x1–“(Θ1(1))2”–>z22 x2–“(Θ2(1))1”–>z22 x2–“(Θ2(1))2”–>z12 a12–“(Θ1(2))1”–>z13 a12–“(Θ1(2))2”–>z23 a22–“(Θ2(2))1”–>z23 a22–“(Θ2(2))2”–>z13 z12–g–>a12 z22– g–>a22 z13–g–>a13 z23–g–>a23 a13-.->y1-.->j a23-.->y2-.->j subgraph x x1((x1)) x2((x2)) end subgraph 第一层 direction LR z12((“z1(2)”)) a12((“a1(2)”)) z22((“z2(2)”)) a22((“a2(2)”)) end subgraph 第二层 z13((“z1(3)”)) a13((“a1(3)”)) z23((“z2(3)”)) a23((“a2(3)”)) end subgraph y y1((ŷ1)) y2((ŷ2)) end j((“J(θ)”))
如图(省略了偏置),输入数据 为 \(\boldsymbol x=\begin{bmatrix}x_1\\x_2\end{bmatrix}\) ,实际输出 为 \(\boldsymbol y=\begin{bmatrix}y_1\\y_2\end{bmatrix}\)
这张图上表示了所有的运算,例如:
\[a_1^{\left(2\right)}=g\left(z_1^{\left(2\right)}\right) \]
\[z_2^{\left(2\right)}=\left(\Theta_1^{\left(1\right)}\right)_2x_1+\left(\Theta_2^{\left(1\right)}\right)_2x_2 \]
同时,此图认为预测输出 为 \(\hat y_1=a_1^{\left(3\right)}\) ,即有误差 (注意此处不是定义而是结论):
\[\delta_1^{\left(3\right)}=\hat y_1-y_1=a_1^{\left(3\right)}-y_1 \]
下面我们将上列函数改写成对应元素的写法,先作定义:
\(L\) :被 \(\Theta\) 作用的层
\(m\) : \(L\) 层单元数量,用 \(j\) 进行遍历(即 \(j\in\left\{1,2,\cdots,m\right\}\) )
\(n\) : \(L+1\) 层单元数量,用 \(i\) 进行遍历
综上可得,若 \(L\) 是倒数第二层,则给出定义 :
\[\begin{align}\delta_i^{\left(L+1\right)} &=\frac{\partial J}{\partial
z_i^{\left(L+1\right)}}\\ &=\frac{\partial J}{\partial
a_i^{\left(L+1\right)}}&&\cdot \frac{\partial a_i^{\left(L+1\right)}}{\partial
z_i^{\left(L+1\right)}}\
&=\left(\frac{-y_i}{a_i^{\left(L+1\right)}}+\frac{1-y_i}{1-a_i^{\left(L+1\right)}}\right)&&\cdot
g^\prime z_i^{\left(L+1\right)}\
&=\left(\frac{-y_i}{a_i^{\left(L+1\right)}}+\frac{1-y_i}{1-a_i^{\left(L+1\right)}}\right)&&\cdot
a_i^{\left(L+1\right)}\left(1-a_i^{\left(L+1\right)}\right)\
&=a_i^{\left(L+1\right)}-y_i \end{align}\]
将同一层 \(\delta_i^{\left(L+1\right)}\) 合并为矩阵得( \(\boldsymbol\delta,\boldsymbol a,\boldsymbol y\) 都是列向量):
\[\boldsymbol\delta^{\left(L+1\right)}=\boldsymbol a^{\left(L+1\right)}-\boldsymbol y \]
下面推隐含层,以第一个单元为例:
\[\begin{align} \delta_1^{\left(2\right)}&=\frac{\partial J}{\partial
z_1^{\left(2\right)}}\\ &=\frac{\partial J}{\partial z_1^{\left(3\right)}}&&
\cdot\frac{\partial z_1^{\left(3\right)}}{\partial a_1^{\left(2\right)}}&&
\cdot\frac{\partial a_1^{\left(2\right)}}{\partial z_1^{\left(2\right)}}&&+
\frac{\partial J}{\partial z_2^{\left(3\right)}}&& \cdot\frac{\partial
z_2^{\left(3\right)}}{\partial a_1^{\left(2\right)}}&& \cdot\frac{\partial
a_1^{\left(2\right)}}{\partial z_1^{\left(2\right)}}\
&=\delta_1^{\left(3\right)}&& \cdot\left(\Theta_1^{\left(2\right)}\right)_1&&
\cdot g^\prime z_1^{\left(2\right)}&&+ \delta_2^{\left(3\right)}&&
\cdot\left(\Theta_1^{\left(2\right)}\right)_2&& \cdot g^\prime
z_1^{\left(2\right)} \end{align}\]
令:
\[\left\{\begin{align}
\boldsymbol\delta^{\left(L\right)}&=\begin{bmatrix}\delta_1^{\left(L\right)}\\\delta_2^{\left(L\right)}\\\vdots\\\delta_n^{\left(L\right)}\end{bmatrix}\
\boldsymbol\Theta_i^{\left(L\right)}&=\begin{bmatrix}
\left(\Theta_i^{\left(L\right)}\right)_1&
\left(\Theta_i^{\left(L\right)}\right)_2& \cdots&
\left(\Theta_i^{\left(L\right)}\right)_n \end{bmatrix}\end{align}\right.\]
可将上式化为矩阵:
\[\delta_1^{\left(2\right)} =\boldsymbol\Theta_1^{\left(2\right)}\boldsymbol\delta^{\left(3\right)} \cdot g^\prime z_1^{\left(2\right)}\]
由上,可写出递推普式 :
\[\delta_j^{\left(L\right)} =\boldsymbol\Theta_j^{\left(L\right)}\boldsymbol\delta^{\left(L+1\right)}\cdot g^\prime z_j^{\left(L\right)}\]
其中最后一层:
\[\boldsymbol\delta^{\left(Last\right)}=\boldsymbol a^{\left(Last\right)}-\boldsymbol y \]
上一篇:何时使用GraphQL、gRPC
下一篇:MFAN论文阅读笔记(待复现)