AI engineering glossary · ML fundamentals
What is VC dimension?
VC dimension (also called Vapnik-Chervonenkis dimension): A theoretical measure of a model class's flexibility: the largest number of points it can label in every possible way without error. Higher values mean a richer class that needs more data to generalise reliably. It connects capacity to guarantees on the gap between training and test error.
VC dimension: an example
A straight line in a plane can separate any 3 points in every labelling but not all labellings of 4 points, so its value is 3.
Related terms
- Model capacity
- Hypothesis space
- PAC learning
- Sample complexity
More ML fundamentals terms
- Weak supervision
- Ablation study
- Active learning
- Akaike information criterion
- Annotation
- Baseline model
- Bayesian information criterion
- Bias error
Where you learn it
VC dimension is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.