The VC dimension has utility in statistical learning theory, because it can predict a probabilistic upper bound on the test error of a classification model.
The bound on the test error of a classification model (on data that is drawn i.i.d. from the same distribution as the training set) is given by
with probability, where is the VC dimension of the classification model, and is the size of the training set (restriction: this formula is valid when ). Similar complexity bounds can be derived using Rademacher complexity, but Rademacher complexity can sometimes provide more insight than VC dimension calculations into such statistical methods such as those using kernels.
In computational geometry, VC dimension is one of the critical parameters in the size of ε-nets, which determines the complexity of approximation algorithms based on them; range sets without finite VC dimension may not have finite ε-nets at all.
Read more about this topic: VC Dimension
Other articles related to "uses, use":
... Waste management often has a soil component ... Septic drain fields treat septic tank effluent using aerobic soil processes ...
... Other applications are short-circuit-proof extra-low voltage transformers for toys or doorbell installations. ...
... Over the past 30 years the end use for linen has changed dramatically ... Linen uses range from bed and bath fabrics (tablecloths, dish towels, bed sheets, etc.), home and commercial furnishing items (wallpaper/wall coverings, upholstery ... yarn for handsewing the uppers of moccasin-style shoes (loafers), but its use has been replaced by synthetics ...