Mercurial > hg > camir-aes2014

annotate toolboxes/FullBNT-1.0.7/netlab3.3/glmunpak.m @ 0:e9a9cd732c1e tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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 = glmunpak(net, w)
wolffd@0 2 %GLMUNPAK Separates weights vector into weight and bias matrices.
wolffd@0 3 %
wolffd@0 4 % Description
wolffd@0 5 % NET = GLMUNPAK(NET, W) takes a glm network data structure NET and a
wolffd@0 6 % weight vector W, and returns a network data structure identical to
wolffd@0 7 % the input network, except that the first-layer weight matrix W1 and
wolffd@0 8 % the first-layer bias vector B1 have been set to the corresponding
wolffd@0 9 % elements of W.
wolffd@0 10 %
wolffd@0 11 % See also
wolffd@0 12 % GLM, GLMPAK, GLMFWD, GLMERR, GLMGRAD
wolffd@0 13 %
wolffd@0 14
wolffd@0 15 % Copyright (c) Ian T Nabney (1996-2001)
wolffd@0 16
wolffd@0 17 % Check arguments for consistency
wolffd@0 18 errstring = consist(net, 'glm');
wolffd@0 19 if ~errstring
wolffd@0 20 error(errstring);
wolffd@0 21 end
wolffd@0 22
wolffd@0 23 if net.nwts ~= length(w)
wolffd@0 24 error('Invalid weight vector length')
wolffd@0 25 end
wolffd@0 26
wolffd@0 27 nin = net.nin;
wolffd@0 28 nout = net.nout;
wolffd@0 29 net.w1 = reshape(w(1:nin*nout), nin, nout);
wolffd@0 30 net.b1 = reshape(w(nin*nout + 1: (nin + 1)*nout), 1, nout);