What is Overfitting?
TL;DR
When an AI model becomes too closely fitted to training data, causing poor performance on new, unseen data.
Overfitting: Definition & Explanation
Overfitting occurs when an AI model memorizes the patterns and noise in training data too closely, leading to degraded prediction accuracy on new, unseen data. The telltale symptom is very high accuracy on training data but significantly lower accuracy on test data. Common causes include insufficient training data, excessive model complexity, and too many training iterations. Effective countermeasures include data augmentation, regularization (L1/L2 regularization, dropout), early stopping, cross-validation, and batch normalization. It is one of the most critical issues in practical machine learning, and proper handling directly impacts whether a model is usable in production.