wolffd@0: function [e, edata, eprior] = rbferr(net, x, t)
wolffd@0: %RBFERR	Evaluate error function for RBF network.
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %	E = RBFERR(NET, X, T) takes a network data structure NET together
wolffd@0: %	with a matrix X of input vectors and a matrix T of target vectors,
wolffd@0: %	and evaluates the appropriate error function E depending on
wolffd@0: %	NET.OUTFN.  Each row of X corresponds to one input vector and each
wolffd@0: %	row of T contains the corresponding target vector.
wolffd@0: %
wolffd@0: %	[E, EDATA, EPRIOR] = RBFERR(NET, X, T) additionally returns the data
wolffd@0: %	and prior components of the error, assuming a zero mean Gaussian
wolffd@0: %	prior on the weights with inverse variance parameters ALPHA and BETA
wolffd@0: %	taken from the network data structure NET.
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	RBF, RBFFWD, RBFGRAD, RBFPAK, RBFTRAIN, RBFUNPAK
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: % Check arguments for consistency
wolffd@0: switch net.outfn
wolffd@0: case 'linear'
wolffd@0:    errstring = consist(net, 'rbf', x, t);
wolffd@0: case 'neuroscale'
wolffd@0:    errstring = consist(net, 'rbf', x);
wolffd@0: otherwise
wolffd@0:    error(['Unknown output function ', net.outfn]);
wolffd@0: end
wolffd@0: if ~isempty(errstring);
wolffd@0:   error(errstring);
wolffd@0: end
wolffd@0: 
wolffd@0: switch net.outfn
wolffd@0: case 'linear'
wolffd@0:    y = rbffwd(net, x);
wolffd@0:    edata = 0.5*sum(sum((y - t).^2));
wolffd@0: case 'neuroscale'
wolffd@0:    y = rbffwd(net, x);
wolffd@0:    y_dist = sqrt(dist2(y, y));
wolffd@0:    % Take t as target distance matrix
wolffd@0:    edata = 0.5.*(sum(sum((t-y_dist).^2)));
wolffd@0: otherwise
wolffd@0:    error(['Unknown output function ', net.outfn]);
wolffd@0: end
wolffd@0: 
wolffd@0: % Compute Bayesian regularised error
wolffd@0: [e, edata, eprior] = errbayes(net, edata);
wolffd@0: