我们来复习上一节的知识:
假设函数:
h
θ
(
x
)
=
θ
0
+
θ
1
x
h_\theta(x)=\theta_0+\theta_1x
hθ(x)=θ0+θ1x
参数:
θ
0
,
θ
1
\theta_0,\theta_1
θ0,θ1
代价函数:
J
(
θ
0
,
θ
1
)
=
1
2
m
∑
i
=
1
i
=
m
(
h
(
x
i
)
−
y
i
)
2
J(\theta_0,\theta_1)=\frac{1}{2m}\sum_{i=1}^{i=m}(h(x^i)-y^i)^2
J(θ0,θ1)=2m1∑i=1i=m(h(xi)−yi)2
目标:求得当
J
(
θ
0
,
θ
1
)
J(\theta_0,\theta_1)
J(θ0,θ1)最小时的
θ
0
,
θ
1
\theta_0,\theta_1
θ0,θ1值
做一个简化,令:
h
θ
(
x
)
=
θ
1
x
h_\theta(x)=\theta_1x
hθ(x)=θ1x
我们可以画出假设函数和代价函数的值。可知,当
θ
1
=
1
\theta_1=1
θ1=1时,有
h
θ
(
x
)
=
x
h_\theta(x)=x
hθ(x)=x
J
(
θ
1
=
1
)
=
1
2
∗
3
∗
[
(
1
−
1
)
2
+
(
2
−
2
)
2
+
(
3
−
3
)
2
]
=
0
J(\theta_1=1)=\frac{1}{2*3}*[(1-1)^2+(2-2)^2+(3-3)^2]=0
J(θ1=1)=2∗31∗[(1−1)2+(2−2)2+(3−3)2]=0
当
θ
1
=
0.5
\theta_1=0.5
θ1=0.5时,有
h
θ
(
x
)
=
0.5
x
h_\theta(x)=0.5x
hθ(x)=0.5x
J
(
θ
1
=
0.5
)
=
1
2
∗
3
∗
[
(
0.5
−
1
)
2
+
(
1
−
2
)
2
+
(
1.5
−
3
)
2
]
=
0.58
J(\theta_1=0.5)=\frac{1}{2*3}*[(0.5-1)^2+(1-2)^2+(1.5-3)^2]=0.58
J(θ1=0.5)=2∗31∗[(0.5−1)2+(1−2)2+(1.5−3)2]=0.58
当
θ
1
=
0
\theta_1=0
θ1=0时,有
h
θ
(
x
)
=
0
h_\theta(x)=0
hθ(x)=0
J
(
θ
1
=
0
)
=
1
2
∗
3
∗
[
(
0
−
1
)
2
+
(
0
−
2
)
2
+
(
0
−
3
)
2
]
=
2.3
J(\theta_1=0)=\frac{1}{2*3}*[(0-1)^2+(0-2)^2+(0-3)^2]=2.3
J(θ1=0)=2∗31∗[(0−1)2+(0−2)2+(0−3)2]=2.3
据此我们可以作出
h
θ
(
x
)
h_\theta(x)
hθ(x)和
J
(
θ
1
)
J(\theta_1)
J(θ1)的图
下次我们将继续讨论加上
θ
0
\theta_0
θ0的情形
代价函数的意义
最新推荐文章于 2024-05-22 13:23:29 发布