VC Dimension

Intermediate

A measure of a model class’s expressive capacity based on its ability to shatter datasets.

Full Definition

A measure of a model class’s expressive capacity based on its ability to shatter datasets.

Keywords

capacity complexity

Domains

AI Economics & Strategy

Related Terms

Rademacher Complexity related to

Measures a model’s ability to fit random noise; used to bound generalization error.

 Bias Term related to

Systematic error introduced by simplifying assumptions in a learning algorithm.

 Variance Term related to

Error due to sensitivity to fluctuations in the training dataset.

 Information Gain related to

Reduction in uncertainty achieved by observing a variable; used in decision trees and active learning.

 Computational Learning Theory related to

A theoretical framework analyzing what classes of functions can be learned, how efficiently, and with what guarantees.

 PAC Learning related to

A model is PAC-learnable if it can, with high probability, learn an approximately correct hypothesis from finite samp...

Concept Map

See how VC Dimension connects to other concepts.

Open Knowledge Graph