Hi. I am a little bit confused here. Isn’t the 11% dev set error and 0.1% training set error indicates that the classifier is overfitting on the dev set? Or is there something wrong on my understandning? Thanks.
what is the meaning of the overfitting it mean that when the model gives accurate predictions for training data but not for new data
what is the meaning if the fitting the fitting is a measure of how well a machine learning model generalizes to similar data to that on which it was trained
So that the model is overfitted on the training data, so the training error is 0.1% that’s mean that the model generate similar data to the training data, and the 11% dev set error mean that the model didn’t fit the new data(dev set)
Cheers,
Abdelrahman
Thanks. I was always think that overfitting is with respect to the test or dev set. Seems like I am wrong.