AI engineering glossary · ML fundamentals
What is generalisation?
Generalisation (also called Generalization): A model's ability to perform well on new data it has never seen, not just on the examples it learned from. It is the real goal of machine learning. A model that only memorises its training data is useless in practice, however impressive its training results look.
Generalisation: an example
A model trained on invoices from 2023 that still reads 2024 invoices accurately is generalising.
Related terms
More ML fundamentals terms
- Generalisation error
- Generalisation gap
- Generative model
- Grid search
- Ground truth
- Group k-fold
- Holdout method
- Hyperparameter
Where you learn it
Generalisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.