Quantcast
Channel: Interview question: train/test error and "best" model - Cross Validated
Browsing all 2 articles
Browse latest View live

Answer by holy_schmitt for Interview question: train/test error and "best" model

I would agree that 2-1-3 seems like the best model, but I think there a couple other factors that could be considered which provide additional support for that answer.The fact that the training curve...

View Article


Image may be NSFW.
Clik here to view.

Interview question: train/test error and "best" model

I recently had a puzzling interview question and I am wondering whether anybody can tell me the intended answer.The question shows train and test error for three models plotted against the number of...

View Article
Browsing all 2 articles
Browse latest View live