Back to Glossary

Overfitting

過学習(かがくしゅう)

IntermediateCore Concepts

When a model learns the training data too well, including its noise and quirks, and performs poorly on new, unseen data.

Why It Matters

Overfitting means your model memorized answers instead of learning patterns — it won't generalize to real-world use.

Example in Practice

A model that scores 99% on training data but only 60% on new test data.

Want to understand AI, not just define it?

Our courses teach you to build with these concepts, not just memorize them.