ICPR
2004
IEEE
15 years 17 days ago
2004
IEEE
In this paper we describe two related approaches to estimating the sample sizes required to statistically compare the performance of two classifiers: acceptable failure rates (AFR...
ICPR
2006
IEEE
15 years 17 days ago
2006
IEEE
Traditionally, machine learning algorithms have been evaluated in applications where assumptions can be reliably made about class priors and/or misclassification costs. In this pa...