In this post, I am sharing the concept of VC dimension. I hope, the compilation of resources on VC dimension will be helpful to understand the basic concept of VC dimension and how can we find the VC dimension of simple geometric shapes, such as, the line, the rectangle, the square, and the rotating rectangle.
VC dimension (for Vapnik–Chervonenkis dimension)
The VC dimension of non-linear classifier is difficult to calculate, however the VC dimension of a linear classifier is easier to calculate.
Before explaining the VC dimension, lets first understand the related basic concepts. We start with the general position of points. According to wiki "A set of at least
points in 
-dimensional space is said to be in general linear position(or just general position) if no hyperplane contains more than points. In more generality, a set containing 
points, for arbitrary , is in general linear position if and only if no 
-dimensional flat contains all points" Continue reading VC Dimensions ...
VC dimension (for Vapnik–Chervonenkis dimension)
The VC dimension of non-linear classifier is difficult to calculate, however the VC dimension of a linear classifier is easier to calculate.
Before explaining the VC dimension, lets first understand the related basic concepts. We start with the general position of points. According to wiki "A set of at least
points in -dimensional space is said to be in general linear position(or just general position) if no hyperplane contains more than points. In more generality, a set containing points, for arbitrary , is in general linear position if and only if no -dimensional flat contains all points" Continue reading VC Dimensions ...
No comments:
Post a Comment