gpcm-class: Gaussian Process Classification (GPC) models class

In GPCsign: Gaussian Process Classification as Described in Bachoc et al. (2020)

Gaussian Process Classification (GPC) models class

Description

S4 class for GPC models.

Slots

d

Object of class "integer". The spatial dimension.

n

Object of class "integer". The number of observations.

X

Object of class "matrix". The design of experiments.

y

Object of class "matrix". The vector of binary observations at design points (+/-1) corresponding to the class labels.

X.std

Object of class "numeric". The vector of standard deviation values of design points.

X.mean

Object of class "numeric". The vector of mean values of design points.

call

Object of class "language". User call reminder.

coef.m

Object of class "numeric". Mean coefficient of latent GP.

coef.cov

Object of class "numeric". Covariance coefficients of latent GP.

covariance

Object of class "covKernel". A DiceKriging object specifying the covariance structure.

noise.flag

Object of class "logical". Are the observations noisy?

noise.var

Object of class "numeric". Nugget effect.

param.estim

Object of class "logical". TRUE if at least one parameter is estimated, FALSE otherwise.

lower

Object of class "numeric". Lower bounds for covariance parameters estimation.

upper

Object of class "numeric". Upper bounds for covariance parameters estimation.

logLik

Object of class "numeric". Value of the log-Likelihood at its optimum.

Z_obs

Object of class "matrix". A nobs * nsimu matrix of samples of the latent process at design points.

l

Object of class "numeric". Lower truncation points. Parameter to generate new Z_obs.

u

Object of class "numeric". Upper truncation points. Parameter to generate new Z_obs.

K

Object of class "matrix". Covariance matrix of design points. Parameter to generate new Z_obs

invK

Object of class "matrix". The inverse of the matrix K whose Cholesky decomposition was given.

MeanTransform

object of class "character". 'positive' if coef.m is constrained to be positive by an exponential transform, 'negative' if coef.m is constrained to be negative.

Objects from the Class

To create a gpcm object, use gpcm. See also this function for more details.

Author(s)

Morgane MENZ, Céline HELBERT, Victor PICHENY, François BACHOC. Contributors: Naoual SERRAJI.

See Also

gpcm for more details about slots and to create a gpcm object. {covStruct.create} in DiceKriging to construct a covariance structure.

GPCsign documentation built on April 4, 2025, 1:55 a.m.