Daniel@0: Daniel@0:
Daniel@0:Daniel@0: net = gp(nin, covarfn) Daniel@0: net = gp(nin, covarfn, prior) Daniel@0:Daniel@0: Daniel@0: Daniel@0:
net = gp(nin, covarfn)
takes the number of inputs nin
Daniel@0: for a Gaussian Process model with a single output, together
Daniel@0: with a string covarfn
which specifies the type of the covariance function,
Daniel@0: and returns a data structure net
. The parameters are set to zero.
Daniel@0:
Daniel@0:
The fields in net
are
Daniel@0:
Daniel@0: type = 'gp' Daniel@0: nin = number of inputs Daniel@0: nout = number of outputs: always 1 Daniel@0: nwts = total number of weights and covariance function parameters Daniel@0: bias = logarithm of constant offset in covariance function Daniel@0: noise = logarithm of output noise variance Daniel@0: inweights = logarithm of inverse length scale for each input Daniel@0: covarfn = string describing the covariance function: Daniel@0: 'sqexp' Daniel@0: 'ratquad' Daniel@0: fpar = covariance function specific parameters (1 for squared exponential, Daniel@0: 2 for rational quadratic) Daniel@0: trin = training input data (initially empty) Daniel@0: trtargets = training target data (initially empty) Daniel@0:Daniel@0: Daniel@0: Daniel@0:
net = gp(nin, covarfn, prior)
sets a Gaussian prior on the
Daniel@0: parameters of the model. prior
must contain the fields
Daniel@0: pr_mean
and pr_variance
. If pr_mean
is a scalar,
Daniel@0: then the Gaussian is assumed to be isotropic and the additional fields
Daniel@0: net.pr_mean
and pr_variance
are set. Otherwise,
Daniel@0: the Gaussian prior has a mean
Daniel@0: defined by a column vector of parameters prior.pr_mean
and
Daniel@0: covariance defined by a column vector of parameters prior.pr_variance
.
Daniel@0: Each element of prmean
corresponds to a separate group of parameters, which
Daniel@0: need not be mutually exclusive. The membership of the groups is defined
Daniel@0: by the matrix prior.index
in which the columns correspond to the elements of
Daniel@0: prmean
. Each column has one element for each weight in the matrix,
Daniel@0: in the order defined by the function gppak
, and each element
Daniel@0: is 1 or 0 according to whether the parameter is a member of the
Daniel@0: corresponding group or not. The additional field net.index
is set
Daniel@0: in this case.
Daniel@0:
Daniel@0:
gppak
, gpunpak
, gpfwd
, gperr
, gpcovar
, gpgrad
Copyright (c) Ian T Nabney (1996-9) Daniel@0: Daniel@0: Daniel@0: Daniel@0: