Next: Learning as Search
Up: Review of Machine Learning
Previous: Summary of Design Choices
- store the training examples and pick closest - nearest neighbor
- generate a large number of checker programs and have them play each other, keeping the most successful and elaborating and mutating them in a kind of simulated evolution - genetic algorithms
- analyze or explain to themselves reasons for specific success or failures - explanation-based learning
Patricia Jean Riddle
Wed Jun 23 13:06:34 NZST 1999