17 Mar 2004
CS 3243 - Learning
27
Expressiveness
nDecision trees can express any function of the input attributes.
nE.g., for Boolean functions, truth table row → path to leaf:
n
n
n
n
n
n
n
n
nTrivially, there is a consistent decision tree for any training set with one path to leaf for each example (unless f nondeterministic in x) but it probably won't generalize to new examples
n
nPrefer to find more compact decision trees