Additional mathematical and learning concepts · MLD-1301
VC dimension
A capacity measure based on the largest number of points a hypothesis class can label in every possible binary way.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Study generalization bounds for classifier families.
Original caveat
It is not usually a tight practical performance predictor for deep networks.
Context and aliases
Level: Advanced. Stages: Theory · Training · Evaluation.
Tags: ML · DL.
Aliases: Vapnik-Chervonenkis dimension.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- Mathematics for Machine Learning ↗ · Reference link
- scikit-learn User Guide ↗ · Consulted
- Original reference URL ↗