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
In the example notebook: train_and_evaluate.ipynb
In the function: normalize_data()
Why are you normalizing on different combinations of test + train + valid sets? Isn't this data leakage? in other words: doesn't this pass information about the properties (eg. mean/ distribution) of the test set to the learning algorithm?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
In the example notebook: train_and_evaluate.ipynb
In the function: normalize_data()
Why are you normalizing on different combinations of test + train + valid sets? Isn't this data leakage? in other words: doesn't this pass information about the properties (eg. mean/ distribution) of the test set to the learning algorithm?
Beta Was this translation helpful? Give feedback.
All reactions