camir-aes2014: toolboxes/FullBNT-1.0.7/netlab3.3/gpunpak.m annotate

first hg version after svn

rev	line source
wolffd@0	1 function net = gpunpak(net, hp)
wolffd@0	2 %GPUNPAK Separates hyperparameter vector into components.
wolffd@0	3 %
wolffd@0	4 % Description
wolffd@0	5 % NET = GPUNPAK(NET, HP) takes an Gaussian Process data structure NET
wolffd@0	6 % and a hyperparameter vector HP, and returns a Gaussian Process data
wolffd@0	7 % structure identical to the input model, except that the covariance
wolffd@0	8 % bias BIAS, output noise NOISE, the input weight vector INWEIGHTS and
wolffd@0	9 % the vector of covariance function specific parameters FPAR have all
wolffd@0	10 % been set to the corresponding elements of HP.
wolffd@0	11 %
wolffd@0	12 % See also
wolffd@0	13 % GP, GPPAK, GPFWD, GPERR, GPGRAD
wolffd@0	14 %
wolffd@0	15
wolffd@0	16 % Copyright (c) Ian T Nabney (1996-2001)
wolffd@0	17
wolffd@0	18 % Check arguments for consistency
wolffd@0	19 errstring = consist(net, 'gp');
wolffd@0	20 if ~isempty(errstring);
wolffd@0	21 error(errstring);
wolffd@0	22 end
wolffd@0	23 if net.nwts ~= length(hp)
wolffd@0	24 error('Invalid weight vector length');
wolffd@0	25 end
wolffd@0	26
wolffd@0	27 net.bias = hp(1);
wolffd@0	28 net.noise = hp(2);
wolffd@0	29
wolffd@0	30 % Unpack input weights
wolffd@0	31 mark1 = 2 + net.nin;
wolffd@0	32 net.inweights = hp(3:mark1);
wolffd@0	33
wolffd@0	34 % Unpack function specific parameters
wolffd@0	35 net.fpar = hp(mark1 + 1:size(hp, 2));
wolffd@0	36

Mercurial > hg > camir-aes2014