https://blog.csdn.net/m0_37769093/article/details/107732606
softmax 函数如下所示：
yi=exp(xi)∑j=1nexp(xj) y_{i} = \frac{\exp(x_{i})}{\sum_{j=1}^{n}{\exp(x_j)}} yi=∑j=1nexp(xj)exp(xi)
softmax求导如下：
i=ji = ji=j 的情况：
∂yi∂xi=exp(xi)∑j=1nexp(xj)−(exp(xi))2(∑j=1nexp(xj))2
\frac{\partial y_{i}}{\partial x_{i}} = \frac{\exp(x_{i})}{\sum_{j=1}^{n}{\exp(x_j)}} - \frac{(\exp(x_{i}))^2}{(\sum_{j=1}^{n}{\exp(x_j)})^2}
∂xi∂yi=∑j=1nexp(xj)exp(xi)−(∑j=1nexp(xj))2(exp(xi))2
∂yi∂xi=yi−(yi)2
\frac{\partial y_{i}}{\partial x_{i}} = y_{i} - (y_{i})^2
∂xi∂yi=yi−(yi)2
i≠ji \neq ji=j 的情况：
∂yi∂xj=−(exp(xi)×exp(xj))(∑j=1nexp(xj))2
\frac{\partial y_{i}}{\partial x_{j}} = - \frac{(\exp(x_{i})\times\exp(x_{j}))}{(\sum_{j=1}^{n}{\exp(x_j)})^2}
∂xj∂yi=−(∑j=1nexp(xj))2(exp(xi)×exp(xj))
∂yi∂xj=−yiyj
\frac{\partial y_{i}}{\partial x_{j}} = - y_{i}y_{j}
∂xj∂yi=−yiyj
扫一扫
39万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
