AI engineering glossary · ML fundamentals
What is generalisation gap?
Generalisation gap: The difference between a model's performance on data it trained on and on unseen data. A large gap signals memorisation of the training set. Tracking it is a quick way to spot trouble and decide whether more data, simpler models or regularisation would help.
Generalisation gap: an example
Accuracy of 99% on training data but 82% on validation data shows a gap of 17 percentage points.
Related terms
More ML fundamentals terms
- Generative model
- Grid search
- Ground truth
- Group k-fold
- Holdout method
- Hyperparameter
- Hyperparameter tuning
- Hypothesis space
Where you learn it
Generalisation gap is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.