0
点赞
收藏
分享

微信扫一扫

Python深度学习基础(五)——SoftMax函数反向传递公式推导及代码实现

倪雅各 2022-03-31 阅读 12

SoftMax函数反向传递公式推导及代码实现

SoftMax函数介绍

简介

softmax函数是常用的输出层函数,常用来解决互斥标签的多分类问题。当然由于他是非线性函数,也可以作为隐藏层函数使用

公式

假设我们有若干输入[x1, x2, x3…xn],对应的输出为[y1, y2, y3…yn],对于SoftMax函数我们有
y i = e x i ∑ k = 0 e x k y_i= \frac{e^{x_i}}{\sum_{k=0} e^{^{x_k}}} yi=k=0exkexi

图像

在这里插入图片描述

反向传递公式推导

SoftMax函数比较特殊,他有多个输入和输出,并且每个输出与所有的输入都有关,所以这个函数输出对于多个输入都有一个偏导数,也就是SoftMax可以得到多个偏导数。对于SoftMax我们有两种情况

当输入坐标与输出坐标相对应时

∂ y i ∂ x j = ∂ y i ∂ x i \frac{\partial y_i}{\partial {x_j}}=\frac{\partial y_i}{\partial {x_i}} xjyi=xiyi
= e x i ⋅ ( ∑ k , i = j e x i ) − e x i ⋅ e x i ( ∑ k , i = j e x k ) 2 = \frac{e^{x_i} \cdot (\sum_{k,i=j} e^{x_i})-e^{x_i} \cdot e^{x_i}}{(\sum_{k, i=j}e^{x_k})^2} =(k,i=jexk)2exi(ki=jexi)exiexi
= e x i ∑ k , i = j e x k − ( e x i ∑ k , i = j e x k ) 2 =\frac{e^{x_i}}{\sum_{k, i=j}e^{x_k}}-(\frac{e^{x_i}}{\sum_{k, i=j}e^{x_k}})^2 =k,i=jexkexi(k,i=jexkexi)2
= y i ( 1 − y i ) =y_i(1-y_i) =yi(1yi)

当输入坐标与输出坐标不对应时

∂ y i ∂ x j = − e x i ⋅ e x j ( ∑ k e x k ) 2 \frac{\partial y_i}{\partial {x_j}}= -\frac{e^{x_i} \cdot e^{x_j}}{(\sum_ke^{x_k})^2} xjyi=(kexk)2exiexj
= − e x i ∑ k , i ! = j e x k ⋅ e x j ∑ k , i ! = j e x k = − y i ⋅ y j =-\frac{e^{x_i}}{\sum_{k, i!=j}e^{x_k}} \cdot \frac{e^{x_j}}{\sum_{k, i!=j}e^{x_k}}=-y_i \cdot y_j =k,i!=jexkexik,i!=jexkexj=yiyj

两种情况合并

∂ y i ∂ x j = e x i ∑ k , i = j e x k − ( e x i ∑ k , i = j e x k ) 2 − e x i ∑ k , i ! = j e x k ⋅ e x j ∑ k , i ! = j e x i = e x i ∑ k , i = j e x k − e x i ⋅ e x j ( ∑ k e x k ) 2 = y i − y i ⋅ y j \frac{\partial y_i}{\partial x_j}=\frac{e^{x_i}}{\sum_{k, i=j}e^{x_k}}-(\frac{e^{x_i}}{\sum_{k, i=j}e^{x_k}})^2-\frac{e^{x_i}}{\sum_{k, i!=j}e^{x_k}} \cdot \frac{e^{x_j}}{\sum_{k, i!=j}e^{x_i}} \\ = \frac{e^{x_i}}{\sum_{k, i=j}e^{x_k}}-\frac{e^{x_i} \cdot e^{x_j}}{(\sum_{k}e^{x_k})^2}=y_i -y_i \cdot y_j xjyi=k,i=jexkexi(k,i=jexkexi)2k,i!=jexkexik,i!=jexiexj=k,i=jexkexi(kexk)2exiexj=yiyiyj

∂ y ∂ x = y ⋅ ( 1 − y ) \frac{\partial y}{\partial x}=y \cdot (1-y) xy=y(1y)

代码实现

class SoftMax():
    def __init__(self):
        pass
    def _softmax(self,x):
        x = x.T
        x = x - np.max(x, axis=0)
        y = np.exp(x) / np.sum(np.exp(x), axis=0)
        return y.T
    
    def forward(self,input):
        return self._softmax(input)
    
    def backward(self, input, grad_output):
        out = self.forward(input)
        return grad_output * out * (1 - out)
举报

相关推荐

0 条评论