Hi,
Description of LibSVM mentions that it could provide probability estimation based on Platt scaling for proper confidence values after applying the learned model on a classification dataset.
So when I say calculate confidences, does it calculate probability estimation or the the confidence? Do I need to use any Platt scaling operator to convert this confidence to probability?
Regards,
Vijay
as far as I know it does and you won't need to apply the plat scaling any more.
Greetings,
Sebastian