Skip to content

Commit

Permalink
Updatee 03GradMode.md 更正反向传播参数错误
Browse files Browse the repository at this point in the history
  • Loading branch information
rebornwwp authored Oct 25, 2024
1 parent 004b81f commit bc797f5
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion 05Framework/02AutoDiff/03GradMode.md
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ $$
转化成如上 DAG(有向无环图)结构之后,我们可以很容易分步计算函数的值,并求取它每一步的导数值,然后,我们把 $df/dx_1$ 求导过程利用链式法则表示成如下的形式:

$$
\dfrac{df}{dx_1}= \dfrac{dv_{-1}}{dx_1} \cdot (\dfrac{dv_{1}}{dv_{-1}} \cdot \dfrac{dv_{4}}{dv_{1}} + \dfrac{dv_{2}}{dv_{-1}} \cdot \dfrac{dv_{4}}{dx_{2}}) \cdot \dfrac{dv_{5}}{dv_{4}} \cdot \dfrac{df}{dv_{5}}
\dfrac{df}{dx_1}= \dfrac{dv_{-1}}{dx_1} \cdot (\dfrac{dv_{1}}{dv_{-1}} \cdot \dfrac{dv_{4}}{dv_{1}} + \dfrac{dv_{2}}{dv_{-1}} \cdot \dfrac{dv_{4}}{dv_{2}}) \cdot \dfrac{dv_{5}}{dv_{4}} \cdot \dfrac{df}{dv_{5}}
$$

> 整个求导可以被拆成一系列微分算子的组合。
Expand Down

0 comments on commit bc797f5

Please sign in to comment.