CS 327: Artificial Intelligence

Assignment: Decision Trees

Assigned on Tuesday, 1/28.
Due on paper in class on Monday, 2/3.

Genetic algorithms have been proposed as a technique for learning decision trees.

1. Why would one think about using genetic algorithms for this purpose instead of ID3? Doesn't ID3 find the best possible solution? If not, why would genetic algorithms potentially do better or faster?

2. Indicate an appropriate chromosome representation, fitness function, and operators for crossover, mutation, and inversion.