Sample width for multi-category classifiers
Anthony, Martin
; and Ratsaby, Joel
(2012)
Sample width for multi-category classifiers
Technical Report.
RUTCOR, Rutgers University, Piscataway, New Jersey, USA.
; and Ratsaby, Joel
(2012)
Sample width for multi-category classifiers
Technical Report.
RUTCOR, Rutgers University, Piscataway, New Jersey, USA.
In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are multi-category and are defined on some arbitrary metric space.
Full text not available from this repository.
Downloads