Next: Overfitting in Decision Trees
Up: Decision Tree Learning
Previous: Occam's razor
- noise in data, number of training instances too small
- Given a hypothesis space
, a hypothesis
is said
to overfit the training data if there exists some alternative
hypothesis
, such that
has a smaller error
than
over the training examples, but
has
a smaller error than
over the entire distribution of instances.
Patricia Jean Riddle
Wed Jun 23 13:06:34 NZST 1999