.TH "mlpack::kernel" 3 "Tue Sep 9 2014" "Version 1.0.10" "MLPACK" \" -*- nroff -*-
.ad l
.nh
.SH NAME
mlpack::kernel \- 
.PP
Kernel functions\&.  

.SH SYNOPSIS
.br
.PP
.SS "Classes"

.in +1c
.ti -1c
.RI "class \fBCosineDistance\fP"
.br
.RI "\fIThe cosine distance (or cosine similarity)\&. \fP"
.ti -1c
.RI "class \fBEpanechnikovKernel\fP"
.br
.RI "\fIThe Epanechnikov kernel, defined as\&. \fP"
.ti -1c
.RI "class \fBExampleKernel\fP"
.br
.RI "\fIAn example kernel function\&. \fP"
.ti -1c
.RI "class \fBGaussianKernel\fP"
.br
.RI "\fIThe standard Gaussian kernel\&. \fP"
.ti -1c
.RI "class \fBHyperbolicTangentKernel\fP"
.br
.RI "\fIHyperbolic tangent kernel\&. \fP"
.ti -1c
.RI "class \fBKernelTraits\fP"
.br
.RI "\fIThis is a template class that can provide information about various kernels\&. \fP"
.ti -1c
.RI "class \fBKernelTraits< CosineDistance >\fP"
.br
.RI "\fIKernel traits for the cosine distance\&. \fP"
.ti -1c
.RI "class \fBKernelTraits< EpanechnikovKernel >\fP"
.br
.RI "\fIKernel traits for the Epanechnikov kernel\&. \fP"
.ti -1c
.RI "class \fBKernelTraits< GaussianKernel >\fP"
.br
.RI "\fIKernel traits for the Gaussian kernel\&. \fP"
.ti -1c
.RI "class \fBKernelTraits< LaplacianKernel >\fP"
.br
.RI "\fIKernel traits of the Laplacian kernel\&. \fP"
.ti -1c
.RI "class \fBKernelTraits< SphericalKernel >\fP"
.br
.RI "\fIKernel traits for the spherical kernel\&. \fP"
.ti -1c
.RI "class \fBKernelTraits< TriangularKernel >\fP"
.br
.RI "\fIKernel traits for the triangular kernel\&. \fP"
.ti -1c
.RI "class \fBKMeansSelection\fP"
.br
.ti -1c
.RI "class \fBLaplacianKernel\fP"
.br
.RI "\fIThe standard Laplacian kernel\&. \fP"
.ti -1c
.RI "class \fBLinearKernel\fP"
.br
.RI "\fIThe simple linear kernel (dot product)\&. \fP"
.ti -1c
.RI "class \fBNystroemMethod\fP"
.br
.ti -1c
.RI "class \fBOrderedSelection\fP"
.br
.ti -1c
.RI "class \fBPolynomialKernel\fP"
.br
.RI "\fIThe simple polynomial kernel\&. \fP"
.ti -1c
.RI "class \fBPSpectrumStringKernel\fP"
.br
.RI "\fIThe p-spectrum string kernel\&. \fP"
.ti -1c
.RI "class \fBRandomSelection\fP"
.br
.ti -1c
.RI "class \fBSphericalKernel\fP"
.br
.ti -1c
.RI "class \fBTriangularKernel\fP"
.br
.RI "\fIThe trivially simple triangular kernel, defined by\&. \fP"
.in -1c
.SH "Detailed Description"
.PP 
Kernel functions\&. 

This namespace contains kernel functions, which evaluate some kernel function $ K(x, y) $ for some arbitrary vectors $ x $ and $ y $ of the same dimension\&. The single restriction on the function $ K(x, y) $ is that it must satisfy Mercer's condition:
.PP
\[ \int \int K(x, y) g(x) g(y) dx dy \ge 0 \].PP
for all square integrable functions $ g(x) $\&.
.PP
The kernels in this namespace all implement the same methods as the \fBExampleKernel\fP class\&. Any additional custom kernels should implement all the methods that class implements; in addition, any method using a kernel should rely on any arbitrary kernel function class having a default constructor and a function
.PP
.PP
.nf
double Evaluate(arma::vec&, arma::vec&);
.fi
.PP
 
.SH "Author"
.PP 
Generated automatically by Doxygen for MLPACK from the source code\&.