Anthony, Martin and Ratsaby, Joel (2012) Sample width for multi-category classifiers. RUTCOR Research Reports, RRR 29-2012. RUTCOR, Rutgers University, Piscataway, New Jersey, USA.Full text not available from this repository.
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.
|Item Type:||Monograph (Technical Report)|
|Additional Information:||© 2012 Rutgers, The State University of New Jersey|
|Library of Congress subject classification:||Q Science > QA Mathematics|
|Sets:||Departments > Mathematics|
|Identification Number:||RRR 29-2012|
|Funders:||IST Programme of the European Community, PASCAL2 Network of Excellence|
|Date Deposited:||29 Nov 2012 14:39|
Actions (login required)
|Record administration - authorised staff only|