Abstract
Histogram rules have the somewhat undesirable property that the rule is less accurate at borders of cells of the partition than in the middle of cells. Looked at intuitively, this is because points near the border of a cell should have less weight in a decision regarding the cell’s center. To remedy this problem, one might introduce the moving window rule, which is smoother than the histogram rule. This classifier simply takes the data points within a certain distance of the point to be classified, and decides according to majority vote. Working formally, let h be a positive number.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer Science+Business Media New York
About this chapter
Cite this chapter
Devroye, L., Györfi, L., Lugosi, G. (1996). Kernel Rules. In: A Probabilistic Theory of Pattern Recognition. Stochastic Modelling and Applied Probability, vol 31. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-0711-5_10
Download citation
DOI: https://doi.org/10.1007/978-1-4612-0711-5_10
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-6877-2
Online ISBN: 978-1-4612-0711-5
eBook Packages: Springer Book Archive