What is overfitting and how do you prevent it?

Overfitting occurs when a model learns the training data too well (including noise), so it performs poorly on new data.

**Signs:** High training accuracy, low test accuracy

**Prevention techniques:**
1. **Regularisation** (L1/L2) — penalise large weights
2. **Dropout** — randomly disable neurons during training
3. **Cross-validation** — use k-fold to evaluate
4. **More data** — collect more training examples
5. **Early stopping** — stop training when validation loss increases
6. **Simpler model** — reduce parameters