You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I cannot understand a technical step. If only the weights related to the observed ratings are updated during backpropagation, this means that the weights related to the ratings of the test set will never be touched.
Is this not a network with extreme overfitting ?
How is it able to generalize ?
The text was updated successfully, but these errors were encountered:
Hi!
I cannot understand a technical step. If only the weights related to the observed ratings are updated during backpropagation, this means that the weights related to the ratings of the test set will never be touched.
Is this not a network with extreme overfitting ?
How is it able to generalize ?
The text was updated successfully, but these errors were encountered: