Overfitting vs Underfitting
After your first training session, you'll need to find the right balance between
two failure modes. Both are normal at this stage. Identifying which problem
you have tells you exactly what to adjust next.
Overfitting: The model learns the quirks and noise in your training data so
well that it fails on new data. It memorized rather than generalized.
Underfitting: The model is too simple to detect meaningful patterns, even in
training data. It hasn't learned enough.
GOOD 
TO KNOW
28

View this content as a flipbook by clicking here.