sigmoid函数的导数是
f
′
(
x
)
=
f
(
x
)
(
1
−
f
(
x
)
)
f ^ { \prime } ( x ) =f ( x ) ( 1 - f ( x ) )
f′(x)=f(x)(1−f(x))
推导过程如下：
1.先将f(x)稍微变形
f
(
x
)
=
1
1
+
e
−
x
=
e
x
e
x
+
1
=
1
−
(
e
x
+
1
)
−
1
f ( x ) = \frac { 1 } { 1 + e ^ { - x } }=\frac { e ^ { x } } { e ^ { x } + 1 } = 1 - \left( e ^ { x } + 1 \right) ^ { - 1 }
f(x)=1+e−x1=ex+1ex=1−(ex+1)−1
2.求导：高等数学-符合求导法则
f
′
(
x
)
=
(
−
1
)
(
−
1
)
(
e
x
+
1
)
−
2
e
x
=
(
1
+
e
−
x
)
−
2
e
−
2
x
e
x
=
(
1
+
e
−
x
)
−
1
⋅
e
−
x
1
+
e
−
x
=
f
(
x
)
(
1
−
f
(
x
)
)
\begin{aligned}f ^ { \prime } ( x )& = ( - 1 ) ( - 1 ) \left( e ^ { x } + 1 \right) ^ { - 2 } e ^ { x } \\ & = \left( 1 + e ^ { - x } \right) ^ { - 2 }e ^ { - 2 x } e ^ { x } \\ & = \left( 1 + e ^ { - x } \right) ^ { - 1 } \cdot \frac { e ^ { - x } } { 1 + e ^ { - x } } \\ & = f ( x ) ( 1 - f ( x ) ) \end{aligned}
f′(x)=(−1)(−1)(ex+1)−2ex=(1+e−x)−2e−2xex=(1+e−x)−1⋅1+e−xe−x=f(x)(1−f(x))
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
