Measuring and Improving the Effectiveness of Representations
- Russ Greiner, Dept of Computing Science; PI of AICML
- Charles Elkan
This report discusses what it means to claim that a representation is an effective encoding of knowledge. We first present dimensions of merit for evaluating representations, based on the view that usefulness is an external property, and is necessarily relative to a specified task. We then provide methods (based on results of mathematical statistics) for reliably measuring effectiveness empirically, and hence for comparing different representations. We also discuss weak but guaranteed methods of improving inadequate representations. Our results are an application of the ideas of formal learning theory to concrete knowledge representation formalisms.
Citation
R. Greiner, C. Elkan. "Measuring and Improving the Effectiveness of Representations". International Joint Conference on Artificial Intelligence (IJCAI), Sydney, Australia, August 1991.| Keywords: | representations, measuring, machine learning |
| Category: | In Conference |
BibTeX
@incollection{Greiner+Elkan:IJCAI91,
author = {Russ Greiner and Charles Elkan},
title = {Measuring and Improving the Effectiveness of Representations},
booktitle = {International Joint Conference on Artificial Intelligence
(IJCAI)},
year = 1991,
}Last Updated: April 24, 2007Submitted by Christian Smith
