Mercurial > hg > camir-aes2014
annotate toolboxes/FullBNT-1.0.7/netlab3.3/mlptrain.m @ 0:e9a9cd732c1e tip
first hg version after svn
| author | wolffd |
|---|---|
| date | Tue, 10 Feb 2015 15:05:51 +0000 |
| parents | |
| children |
| rev | line source |
|---|---|
| wolffd@0 | 1 function [net, error] = mlptrain(net, x, t, its); |
| wolffd@0 | 2 %MLPTRAIN Utility to train an MLP network for demtrain |
| wolffd@0 | 3 % |
| wolffd@0 | 4 % Description |
| wolffd@0 | 5 % |
| wolffd@0 | 6 % [NET, ERROR] = MLPTRAIN(NET, X, T, ITS) trains a network data |
| wolffd@0 | 7 % structure NET using the scaled conjugate gradient algorithm for ITS |
| wolffd@0 | 8 % cycles with input data X, target data T. |
| wolffd@0 | 9 % |
| wolffd@0 | 10 % See also |
| wolffd@0 | 11 % DEMTRAIN, SCG, NETOPT |
| wolffd@0 | 12 % |
| wolffd@0 | 13 |
| wolffd@0 | 14 % Copyright (c) Ian T Nabney (1996-2001) |
| wolffd@0 | 15 |
| wolffd@0 | 16 options = zeros(1,18); |
| wolffd@0 | 17 options(1) = -1; % To prevent any messages at all |
| wolffd@0 | 18 options(9) = 0; |
| wolffd@0 | 19 options(14) = its; |
| wolffd@0 | 20 |
| wolffd@0 | 21 [net, options] = netopt(net, options, x, t, 'scg'); |
| wolffd@0 | 22 |
| wolffd@0 | 23 error = options(8); |
| wolffd@0 | 24 |