Learn R Programming
⚠️There's a newer version (1.08) of this package.Take me there.

gptk (version 1.07)

Gaussian Processes Tool-Kit

Description

The gptk package implements a general-purpose toolkit for Gaussian process regression with a variety of covariance functions (e.g. RBF, Mattern, polynomial, etc). Based on a MATLAB implementation by Neil D. Lawrence. See inst/doc/index.html for more details.

Copy Link

Version

Install

install.packages('gptk')

Monthly Downloads

21

Version

1.07

License

BSD_2_clause + file LICENSE

Maintainer

Alfredo A Kalaitzis

Last Published

October 16th, 2013

Functions in gptk (1.07)

demInterpolation

Gaussian Process Interpolation Demo
basePlot

Plot a contour of the 2D Gaussian distribution with covariance matrix K.
modelExpandParam

Update a model structure with new parameters or update the posterior processes.
gpCreate

Create a GP model with inducing variables/pseudo-inputs.
demAutoOptimiseGp

Gaussian Process Optimisation Demo
cmpndKernParamInit

CMPND kernel parameter initialisation.
gpObjective

Wrapper function for GP objective.
gpPlot

Gaussian Process Plotter
gpLogLikeGradients

Compute the gradients for the parameters and X.
gpDataIndices

Return indices of present data.
expTransform

Constrains a parameter.
gpCovGradsTest

Test the gradients of the likelihood wrt the covariance.
modelOutputGrad

Compute derivatives with respect to params of model outputs.
SCGoptim

Optimise the given function using (scaled) conjugate gradients.
noiseCreate

Initialise a noise structure.
kernParamInit

Kernel parameter initialisation.
gpTest

Test the gradients of the gpCovGrads function and the gp models.
gpOptions

Return default options for GP model.
gpSample

Plot Samples from a GP.
gpScaleBiasGradient

Compute the log likelihood gradient wrt the scales.
noiseParamInit

Noise model's parameter initialisation.
gpComputeM

Compute the matrix m given the model.
gpOut

Evaluate the output of an Gaussian process model.
gpPosteriorMeanVar

Mean and variances of the posterior at points given by X.
rbfKernGradX

Gradient of RBF kernel with respect to input locations.
modelGradientCheck

Check gradients of given model.
optimiDefaultConstraint

Returns function for parameter constraint.
gaussSamp

Sample from a Gaussian with a given covariance.
rbfKernDiagGradX

Gradient of RBF kernel's diagonal with respect to X.
modelExtractParam

Extract the parameters of a model.
gpComputeAlpha

Update the vector `alpha' for computing posterior mean quickly.
modelOut

Give the output of a model for given X.
gpLogLikelihood

Compute the log likelihood of a GP.
gaussianNoiseOut

Compute the output of the GAUSSIAN noise given the input mean and variance.
zeroAxes

A function to move the axes crossing point to the origin.
gpUpdateKernels

Update the kernels that are needed.
gpGradient

Gradient wrapper for a GP model.
gpMeanFunctionGradient

Compute the log likelihood gradient wrt the scales.
kernCreate

Initialise a kernel structure.
cmpndNoiseParamInit

CMPND noise parameter initialisation.
rbfKernParamInit

RBF kernel parameter initialisation.
gpExpandParam

Expand a parameter vector into a GP model.
demOptimiseGp

Gaussian Process Optimisation Demo
whiteKernParamInit

WHITE kernel parameter initialisation.
kernCompute

Compute the kernel given the parameters and X.
gpBlockIndices

Return indices of given block.
gpCovGrads

Sparse objective function gradients wrt Covariance functions for inducing variables.
gaussianNoiseParamInit

GAUSSIAN noise parameter initialisation.
gpExtractParam

Extract a parameter vector from a GP model.
demGpSample

Gaussian Process Sampling Demo
demRegression

Gaussian Process Regression Demo
kernGradient

Compute the gradient wrt the kernel parameters.
gpOptimise

Optimise the inducing variable based kernel.
kernTest

Run some tests on the specified kernel.
gpUpdateAD

Update the representations of A and D associated with the model.
modelGradient

Model log-likelihood/objective error function and its gradient.
kernDiagGradient

Compute the gradient of the kernel's parameters for the diagonal.
kernDiagGradX

Compute the gradient of the kernel wrt X.
whiteKernGradX

Gradient of WHITE kernel with respect to input locations.
multiKernParamInit

MULTI kernel parameter initialisation.
whiteKernDiagGradX

Gradient of WHITE kernel's diagonal with respect to X.
gpPosteriorSample

Plot Samples from a GP Posterior.
demGpCov2D

Gaussian Process 2D Covariance Demo
modelDisplay

Display a model.
noiseOut

Give the output of the noise model given the mean and variance.