5,321
edits
Machine Learning: Difference between revisions
→VC dimension
| Line 198: | Line 198: | ||
</math> | </math> | ||
: for some constants <math>K_1, K_2</math> | : for some constants <math>K_1, K_2</math> | ||
====Growth Function==== | |||
The growth function is maximum number of ways <math>m</math> examples can be labelled using hypotheses from <math>\mathcal{H}</math> | |||
* <math>\tau_H(m) = \max_{|C| = m} |H_C|</math> | |||
;Notes | |||
* If <math>m \leq VCdim(H)</math>, then <math>\tau_H(m) = 2^m</math> | |||
====Sauer's Lemma==== | |||
===Bias-Variance Tradeoff=== | ===Bias-Variance Tradeoff=== | ||