Mercurial > hg > camir-aes2014
annotate toolboxes/FullBNT-1.0.7/netlab3.3/glmpak.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 w = glmpak(net) |
| wolffd@0 | 2 %GLMPAK Combines weights and biases into one weights vector. |
| wolffd@0 | 3 % |
| wolffd@0 | 4 % Description |
| wolffd@0 | 5 % W = GLMPAK(NET) takes a network data structure NET and combines them |
| wolffd@0 | 6 % into a single row vector W. |
| wolffd@0 | 7 % |
| wolffd@0 | 8 % See also |
| wolffd@0 | 9 % GLM, GLMUNPAK, GLMFWD, GLMERR, GLMGRAD |
| wolffd@0 | 10 % |
| wolffd@0 | 11 |
| wolffd@0 | 12 % Copyright (c) Ian T Nabney (1996-2001) |
| wolffd@0 | 13 |
| wolffd@0 | 14 errstring = consist(net, 'glm'); |
| wolffd@0 | 15 if ~errstring |
| wolffd@0 | 16 error(errstring); |
| wolffd@0 | 17 end |
| wolffd@0 | 18 |
| wolffd@0 | 19 w = [net.w1(:)', net.b1]; |
| wolffd@0 | 20 |