wolffd@0: function [net, error] = mlptrain(net, x, t, its);
wolffd@0: %MLPTRAIN Utility to train an MLP network for demtrain
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %
wolffd@0: %	[NET, ERROR] = MLPTRAIN(NET, X, T, ITS) trains a network data
wolffd@0: %	structure NET using the scaled conjugate gradient algorithm  for ITS
wolffd@0: %	cycles with input data X, target data T.
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	DEMTRAIN, SCG, NETOPT
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: options = zeros(1,18);
wolffd@0: options(1) = -1;	% To prevent any messages at all
wolffd@0: options(9) = 0;
wolffd@0: options(14) = its;
wolffd@0: 
wolffd@0: [net, options] = netopt(net, options, x, t, 'scg');
wolffd@0: 
wolffd@0: error = options(8);
wolffd@0: