New Empirical Learning Mechanisms Perform Significantly Better in Real Life Domains
Abstract
New empirical learning mechanisms significantly improve classification accuracy and explanation in real life inexact domains, Properties of these domains are analysed in order to explain global motives of our approach. New mechanisms are shortly described with possible explanations why they perform so well in practical tasks. They construct only ‘good’ rules and implicitly or explicitly use redundant knowledge. Finally, our system GINESYS and testing results in oncological domains are presented.
Cite
Text
Gams and Karalic. "New Empirical Learning Mechanisms Perform Significantly Better in Real Life Domains." International Conference on Machine Learning, 1989. doi:10.1016/B978-1-55860-036-2.50034-5Markdown
[Gams and Karalic. "New Empirical Learning Mechanisms Perform Significantly Better in Real Life Domains." International Conference on Machine Learning, 1989.](https://mlanthology.org/icml/1989/gams1989icml-new/) doi:10.1016/B978-1-55860-036-2.50034-5BibTeX
@inproceedings{gams1989icml-new,
title = {{New Empirical Learning Mechanisms Perform Significantly Better in Real Life Domains}},
author = {Gams, Matjaz and Karalic, Aram},
booktitle = {International Conference on Machine Learning},
year = {1989},
pages = {99-103},
doi = {10.1016/B978-1-55860-036-2.50034-5},
url = {https://mlanthology.org/icml/1989/gams1989icml-new/}
}