wolffd@0: function [y, extra, invhess] = mlpevfwd(net, x, t, x_test, invhess)
wolffd@0: %MLPEVFWD Forward propagation with evidence for MLP
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %	Y = MLPEVFWD(NET, X, T, X_TEST) takes a network data structure  NET
wolffd@0: %	together with the input X and target T training data and input test
wolffd@0: %	data X_TEST. It returns the normal forward propagation through the
wolffd@0: %	network Y together with a matrix EXTRA which consists of error bars
wolffd@0: %	(variance) for a regression problem or moderated outputs for a
wolffd@0: %	classification problem. The optional argument (and return value)
wolffd@0: %	INVHESS is the inverse of the network Hessian computed on the
wolffd@0: %	training data inputs and targets.  Passing it in avoids recomputing
wolffd@0: %	it, which can be a significant saving for large training sets.
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	FEVBAYES
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: [y, z, a] = mlpfwd(net, x_test);
wolffd@0: if nargin == 4
wolffd@0:   [extra, invhess] = fevbayes(net, y, a, x, t, x_test);
wolffd@0: else
wolffd@0:   [extra, invhess] = fevbayes(net, y, a, x, t, x_test, invhess);
wolffd@0: end