Learning Despite Concept Variation by Finding Structure in Attribute-Based Data
Abstract
Learning accuracy depends on concept variation. The accuracy of six learning systems (C4.5, Grove, Greedy, Fringe, LFC and MRP) is compared using a set of forty test concepts. The selection of these concepts was guided by the existence of structured concepts that appear in difficult real-world domains (such as protein folding). Such concepts often have embedded, implicit structure, which may be revealed through explicit relations. Experiments using these benchmark concepts show that concept variation affects systems that find relations, such as MRP, significantly less than the other learners. We analyze this distinctive behavior in terms of concept characteristics and relate it to system performance in real-world domains. 1 MOTIVATION Because there is no hope of finding a universal learner (Watanabe, 1985; Schaffer, 1994; Rao, Gordon, & Spears, 1995), it is important to discover the conditions that favor a given learning system. The vast majority of concepts cannot be...
Cite
Text
Pérez and Rendell. "Learning Despite Concept Variation by Finding Structure in Attribute-Based Data." International Conference on Machine Learning, 1996.Markdown
[Pérez and Rendell. "Learning Despite Concept Variation by Finding Structure in Attribute-Based Data." International Conference on Machine Learning, 1996.](https://mlanthology.org/icml/1996/perez1996icml-learning/)BibTeX
@inproceedings{perez1996icml-learning,
title = {{Learning Despite Concept Variation by Finding Structure in Attribute-Based Data}},
author = {Pérez, Eduardo and Rendell, Larry A.},
booktitle = {International Conference on Machine Learning},
year = {1996},
pages = {391-399},
url = {https://mlanthology.org/icml/1996/perez1996icml-learning/}
}