next up previous
Next: ch3 Up: ch3 Previous: ch3

Inductive Bias in ID3

Note $H$ is the power set of instances $X$


$\ra $Unbiased?


Not really... Preference for short trees, and for those with high information gain attributes near the root

Bias is a preference for some hypotheses, rather than a restriction of hypothesis space $H$

Occam's razor: prefer the shortest hypothesis that fits the data



Don Patterson 2001-12-13