Next: Neural Network Learning
Up: Decision Tree Learning
Previous: Summary
- Overfitting data is an important issue. Therefore methods for
post-pruning are important.
- Very large variety of extensions: post-pruning, handling
real-valued attributes, accommodating missing attribute values,
incrementally refining decision trees, other attribute selection
measures, considering costs associated with instance attributes (or
target values).
Patricia Jean Riddle
Wed Jun 23 13:06:34 NZST 1999