Artificial Intelligence & Machine Learning
Overfitting
Definition
Overfitting is a modeling error in machine learning that occurs when a model learns the training data too well. It learns not only the underlying patterns but also the noise and random fluctuations in the training data, to the extent that it negatively impacts the model's performance on new, unseen data.
Why It Matters
An overfitted model is useless in practice because it cannot generalize to new data. It has memorized the training examples instead of learning the general principles.
Contextual Example
A model trained to identify cats overfits on a training set that only contains pictures of black cats. When shown a picture of a white cat (unseen data), it fails to recognize it as a cat.
Common Misunderstandings
- The opposite of overfitting is underfitting.
- Techniques to prevent overfitting include using more training data, regularization, and dropout.