VC Dimension
Vapnik-Chervonenkis dimension is a theoretical mathematical measure of the capacity, complexity, and expressive power of a machine learning algorithm.
Think of It Like This
Like rating a highly flexible yoga instructor by the absolute maximum number of complex poses they can physically contort themselves into.
It defines the maximum number of data points that a specific hypothesis class (like linear classifiers) can perfectly separate (shatter) for all possible binary label assignments. A higher VC dimension means the model can learn more complex patterns, but mathematically requires exponentially more training data to guarantee generalization.