CCT MENDOZA 20878
CENTRO CIENTIFICO TECNOLOGICO CONICET - MENDOZA
Centro Científico Tecnológico - CCT
artículos
Título:
Linear Discrimination with equicorrelated training vectors
Autor/es:
RICARDO LEIVA
Revista:
JOURNAL OF MULTIVARIATE ANALYSIS
Editorial:
Elsevier
Referencias:
Año: 2007 vol. 98 p. 384 - 409
ISSN:
0047-259X
Resumen:
Fisher´s linear discrimination rule requires uncorrelated training vectors. In this paper a linear discrimination method is developed to be used when the training vectors are equicorrelated. Also, maximum likelihood ratio tests are proposed to decide if the training samples are uncorrelated or equicorrelated.
