On the class distribution labelling step sensitivity of co-training
Text / resource
Text / resource
Co-training can learn from datasets having a small number of labelled examples and a large number of unlabelled ones. It is an iterative algorithm where examples labelled in previous iterations are used to improve the cl...
Idioma English
Acceso abiertoRuta libre sin proxy. Acceso recomendado cuando no hay suscripción activa.
Open Access