A Case-Based Methodology for Feature Weighting Algorithm Recommendation

Authors:
Héctor Núòez;Miquel Sànchez-Marrè
Affiliations:
Instituto Tecnológico de Durango, México;KEMLG, Technical University of Catalonia, Catalonia
Venue:
Proceedings of the 2005 conference on Artificial Intelligence Research and Development
Year:
2005

Citing 3
Cited 0

Technical Note: Selecting a Classification Method by Cross-Validation

Machine Learning
Machine learning, neural and statistical classification

Machine learning, neural and statistical classification
Improving similarity assessment with entropy-based local weighting

ICCBR'03 Proceedings of the 5th international conference on Case-based reasoning: Research and Development

Quantified Score

Hi-index	0.00

Visualization

Abstract

The underlying idea of the methodology proposed in this paper is to provide a new methodology that could select the most appropriate feature weighting algorithm for a given database. The main idea is to implement a case-based system, where cases are formed by description of databases and feature weighting techniques optimising their generalisation accuracy. This methodology recommends the best techniques to be used in a new unknown database or domain.