Overfitting (model memorira podatke iz skupa za treniranje i ne uspijeva na novim podacima) i underfitting (model je previše jednostavan da bi uhvatio obrasce) su dva temeljna problema u ML-u. Uravnotežavanje između njih — postizanje dobre generalizacije — je ključno za izgradnju učinkovitih modela.
Overfitting nasuprot underfitting
OVERFITTING → the model learns the training data TOO well (including noise) →
→ performs great on training data but POORLY on new/unseen data (doesn't generalize)
→ too complex; memorizes rather than learns general patterns
→ like memorizing answers vs understanding the concept
UNDERFITTING → the model is TOO SIMPLE to capture the underlying patterns →
→ performs poorly on BOTH training and new data
→ not enough complexity/capacity to learn the patterns
→ the goal is GENERALIZATION: learn real patterns → perform well on NEW data
