5,322
edits
Machine Learning: Difference between revisions
→Definition
| Line 227: | Line 227: | ||
* To show VCdim is leq n, prove no training set of size n+1 can be shattered by our hypothesis class. | * To show VCdim is leq n, prove no training set of size n+1 can be shattered by our hypothesis class. | ||
* 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==== | ====Theory==== | ||