ModErn Text Analysis
META Enumerates Textual Applications
|
A radial basis function kernel for linear classifiers to adapt them to data that is not linearly separable. More...
#include <radial_basis.h>
Public Member Functions | |
radial_basis (double gamma) | |
Constructs a new radial_basis kernel with the given parameter. More... | |
template<class PostingsData > | |
double | operator() (const PostingsData &first, const PostingsData &second) const |
Computes the value of \(K(first, second)\). | |
Private Attributes | |
double | gamma_ |
\(\gamma\), or equivalently \(-\frac1{2\sigma^2}\), the parameter for the radial basis function. | |
A radial basis function kernel for linear classifiers to adapt them to data that is not linearly separable.
Uses the form of: \(K(x, z) = \exp(\gamma||x-z||_2^2)\)
|
inline |
Constructs a new radial_basis kernel with the given parameter.
gamma | The parameter for the radial basis function. |