rbfkernel-class

polykernel-class

vanillakernel-class

tanhkernel-class

anovakernel-class

besselkernel-class

laplacekernel-class

splinekernel-class

stringkernel-class

fourierkernel-class

kfunction-class

kernel-class

kpar,kernel-method

  The built-in kernel classes in <span class="pkg">kernlab</span>

classes

Kernel-based machine learning methods for classification,
regression, clustering, novelty detection, quantile regression
and dimensionality reduction.  Among other methods 'kernlab'
includes Support Vector Machines, Spectral Clustering, Kernel
PCA, Gaussian Processes and a QP solver.

Alexandros Karatzoglou

kernlab

Kernel-Based Machine Learning Lab

kernel-class function

Objects can be created by calls of the form <code>new("rbfkernel")</code>,
<code>new{"polykernel"}</code>, <code>new{"tanhkernel"}</code>,
<code>new{"vanillakernel"}</code>, <code>new{"anovakernel"}</code>,
<code>new{"besselkernel"}</code>, <code>new{"laplacekernel"}</code>,
<code>new{"splinekernel"}</code>, <code>new{"stringkernel"}</code> or by calling the <code>rbfdot</code>, <code>polydot</code>, <code>tanhdot</code>,
<code>vanilladot</code>, <code>anovadot</code>, <code>besseldot</code>, <code>laplacedot</code>,
<code>splinedot</code>, <code>stringdot</code> functions etc..

Objects from the Class

<dl>
    <dt><code>.Data</code>:</dt><dd>Object of class <code>"function"</code> containing
      the kernel function </dd> <dt><code>kpar</code>:</dt><dd>Object of class <code>"list"</code> containing the
      kernel parameters </dd> </dl> 

Slots

Class <code>"kernel"</code>, directly.
Class <code>"function"</code>, by class <code>"kernel"</code>.

Extends

<dl>
    <dt>kernelMatrix</dt><dd><code>signature(kernel = "rbfkernel", x =
	"matrix")</code>: computes the kernel matrix</dd> <dt>kernelMult</dt><dd><code>signature(kernel = "rbfkernel", x =
	"matrix")</code>: computes the quadratic kernel expression</dd> <dt>kernelPol</dt><dd><code>signature(kernel = "rbfkernel", x =
	"matrix")</code>: computes the kernel expansion</dd> <dt>kernelFast</dt><dd><code>signature(kernel = "rbfkernel", x =
	"matrix"),,a</code>: computes parts or the full kernel matrix, mainly
      used in kernel algorithms where columns of the kernel matrix are
      computed per invocation </dd> </dl> 

kernel-class: Class "kernel" "rbfkernel" "polykernel", "tanhkernel", "vanillakernel"

Description

Arguments

Objects from the Class

Slots

Extends

Methods

See Also

Examples