add third chapter

This commit is contained in:
skindhu 2024-11-02 14:59:27 +08:00
parent 5498cf5935
commit f15fde036b
1 changed files with 4 additions and 4 deletions

View File

@ -1000,11 +1000,11 @@ tensor([[2., 2., 0., 2., 2., 0.],
>
> $$ \text{z_{i}}^{\prime}=\frac{z_{i}}{1-p} \quad \text { (对于未被置零的权重) } $$
>
>
>
> $$ \text{softmax}\left(z_{i}\right)=\frac{e^{z_{i}}}{\sum_{j} e^{z_{j}}} $$
>
>
>
>
> 111
现在,让我们将 dropout 应用于注意力权重矩阵本身: