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

first hg version after svn

rev	line source
wolffd@0	1 function [e, varargout] = neterr(w, net, x, t)
wolffd@0	2 %NETERR Evaluate network error function for generic optimizers
wolffd@0	3 %
wolffd@0	4 % Description
wolffd@0	5 %
wolffd@0	6 % E = NETERR(W, NET, X, T) takes a weight vector W and a network data
wolffd@0	7 % structure NET, together with the matrix X of input vectors and the
wolffd@0	8 % matrix T of target vectors, and returns the value of the error
wolffd@0	9 % function evaluated at W.
wolffd@0	10 %
wolffd@0	11 % [E, VARARGOUT] = NETERR(W, NET, X, T) also returns any additional
wolffd@0	12 % return values from the error function.
wolffd@0	13 %
wolffd@0	14 % See also
wolffd@0	15 % NETGRAD, NETHESS, NETOPT
wolffd@0	16 %
wolffd@0	17
wolffd@0	18 % Copyright (c) Ian T Nabney (1996-2001)
wolffd@0	19
wolffd@0	20 errstr = [net.type, 'err'];
wolffd@0	21 net = netunpak(net, w);
wolffd@0	22
wolffd@0	23 [s{1:nargout}] = feval(errstr, net, x, t);
wolffd@0	24 e = s{1};
wolffd@0	25 if nargout > 1
wolffd@0	26 for i = 2:nargout
wolffd@0	27 varargout{i-1} = s{i};
wolffd@0	28 end
wolffd@0	29 end

Mercurial > hg > camir-aes2014