121 this.
registerProps(
" K ",
" lambda ",
" CGMaxIt ",
" CGTol ",
" MaxStraightInvDim ");
126 copy = general.regression.KernelLS;
129 copy.CGTol= this.
CGTol;
140 M = this.
K^
t*this.
K + this.
lambda*speye(n, n);
171 svidx = 1:size(yi,2);
176 #if 0 //mtoc++: 'set.K'
178 if (isa(value,
" handle ") && ~isa(value,
" data.FileMatrix ")) || (~
ismatrix(value) || ~isa(value,
" double "))
179 error(
" Value must be a data.FileMatrix or a double matrix. ");
192 #if 0 //mtoc++: 'set.lambda'
195 error(" value must be a positive scalar ");
204 #if 0 //mtoc++: 'set.CGMaxIt'
207 error(" value must be a positive
integer scalar ");
216 #if 0 //mtoc++: 'set.CGTol'
217 function
CGTol(value) {
219 error(" value must be a positive real scalar. ");
228 #if 0 //mtoc++: 'set.MaxStraightInvDim'
231 error(" value must be a positive
integer scalar ");
K
The kernel matrix to use for LS regression.
Base class for any KerMor class.
function registerProps(varargin)
Call this method at any class that defines DPCM observed properties.
KERNELLS Least-Squares kernel regression ("Rigde Regression") Since the systems can be considerably l...
CGTol
Tolerance for cg method.
MaxStraightInvDim
Maximum dimension of function for which direct inversion is performed instead of pcg.
static const SUCCESS
Algorithm terminated otherwisely successful.
KerMorObject()
Constructs a new KerMor object.
function ismat = ismatrix(value)
ismatrix: Compatibility function for matlab versions smaller than 2011b
function K = getKernelMatrix()
Computes the kernel matrix for the currently set center data.
function [ a , sf ] = regress(fx, ainit)
Interface for kernel expansion coefficient computation.
double lambda
The regularization term weight.
function [ ai , svidx , sf ] = computeKernelCoefficients(yi, initialai)
Kernel coefficient computation.
function init(kernels.KernelExpansion kexp)
% IKernelCoeffComp interface members Sets the kernel matrix.
function res = isposintscalar(value)
isposintscalar: Backwards-compatibility function for matlab versions greater than 2012a ...
CGMaxIt
Maximum iteration count for the conjugate gradient method.
function res = isposrealscalar(value)
isposintscalar: Backwards-compatibility function for matlab versions greater than 2012a ...
KernelExpansion: Base class for state-space kernel expansions.
StopFlag: Flags that algorithms can use to specify the reason for their termination.