5,337
edits
Machine Learning: Difference between revisions
→VC dimension
| Line 38: | Line 38: | ||
* Number of parameters do not necessarily correspond to VC dimension. | * Number of parameters do not necessarily correspond to VC dimension. | ||
: <math>H=\{h(x)=\sin(\theta x)\}</math> has infinite VC dimension with one parameter | : <math>H=\{h(x)=\sin(\theta x)\}</math> has infinite VC dimension with one parameter | ||
====Theory==== | |||
For all h in H, | |||
* <math>|L_D(h) - L_S(h)| < K_1 \sqrt{ | |||
\frac{VCdim + K_2 log(2/\delta)}{2m}} | |||
</math> | |||