Seonglae ChoDetermine model complexity
Model complexity → high variance in test data.
불확정성 원리같이 AI의 지능한계가 있을 수도 있다.
because this is perspective of model
If a model is too simple and has very few parameters, then it may have large bias and small variance
It may typically suffer from underfitting
If a model is too complex and has very many parameters, then it may suffer from large
variance but small bias and thus overfitting
Theoretical background
mean squared error or risk = bias^2 + variance
