Overfitting

Overfitting occurs when a model memorizes training data instead of learning general patterns.

Signs of Overfitting: - High accuracy on training data - Poor accuracy on test/validation data - Model is too complex for the data

Causes: - Too many parameters - Too little training data - Training too long - Model too complex

• **Prevention Techniques:**
• Regularization: L1, L2 penalties
• Dropout: Randomly disable neurons
• Early Stopping: Stop before overfitting
• Data Augmentation: Create more training data
• Cross-Validation: Test on multiple splits

Opposite Problem: - Underfitting: Model too simple to learn patterns