Artículo
Optimal arrangements of hyperplanes for SVM-based multiclass classification
Autor/es | Blanco Izquierdo, Víctor
Japón Sáez, Alberto Puerto Albandoz, Justo |
Departamento | Universidad de Sevilla. Departamento de Estadística e Investigación Operativa |
Fecha de publicación | 2019-07 |
Fecha de depósito | 2020-01-28 |
Publicado en |
|
Resumen | In this paper, we present a novel approach to construct multiclass classifiers by means of arrangements of hyperplanes. We propose different mixed integer (linear and non linear) programming formulations for the problem ... In this paper, we present a novel approach to construct multiclass classifiers by means of arrangements of hyperplanes. We propose different mixed integer (linear and non linear) programming formulations for the problem using extensions of widely used measures for misclassifying observations where the kernel trick can be adapted to be applicable. Some dimensionality reductions and variable fixing strategies are also developed for these models. An extensive battery of experiments has been run which reveal the powerfulness of our proposal as compared with other previously proposed methodologies. |
Identificador del proyecto | MTM2016-74983-C2-1-R
PP2016-PIP06 SEJ-534 |
Cita | Blanco Izquierdo, V., Japón Sáez, A. y Puerto Albandoz, J. (2019). Optimal arrangements of hyperplanes for SVM-based multiclass classification. Advances in Data Analysis and Classification, 1-25. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Optimal arrangements of hyperplanes ... | 1.151Mb | [PDF] | Ver/ | |