Perturbation: A Means for Guiding Generalization
Abstract
Learning problem solving from examples suffers from three problems. First, there is a strong dependency on the order of the presented examples. Second, each example has its own peculiarities which must be overcome. Third, the size of the generalization space can be huge, even if the instance language is small. By adding perturbation operators to the concept tree each of these problems can be alleviated. This is demonstrated in a system which learns, through interaction with a teacher, to solve simultaneous linear equations.
Cite
Text
Kibler and Porter. "Perturbation: A Means for Guiding Generalization." International Joint Conference on Artificial Intelligence, 1983.Markdown
[Kibler and Porter. "Perturbation: A Means for Guiding Generalization." International Joint Conference on Artificial Intelligence, 1983.](https://mlanthology.org/ijcai/1983/kibler1983ijcai-perturbation/)BibTeX
@inproceedings{kibler1983ijcai-perturbation,
title = {{Perturbation: A Means for Guiding Generalization}},
author = {Kibler, Dennis F. and Porter, Bruce W.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1983},
pages = {415-418},
url = {https://mlanthology.org/ijcai/1983/kibler1983ijcai-perturbation/}
}