Below is a plot of validation loss and training loss for my CNN model.
The validation loss is decreasing with training loss but there is a gap between the two functions.
What does this mean? The model is not overfitting as the validation loss is decreasing, but is something wrong with the model because there is a gap between the two functions?
I'm new to this, so please help.
Overfitting is not necessarily accompanied by the flattening of the validation loss curve - the gap between the loss curves simply indicates that the model is learning relationships that do not apply to the validation data. The first thing I would check in such a scenario is the balance of the sets - do both training and validation sets comprise of an equal distribution of classes/values? Was the entire dataset properly shuffled before assigning 'training' and 'validation' tags to them?
