Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mlppak.htm @ 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
comparison
equal deleted inserted replaced
-1:000000000000 0:e9a9cd732c1e
1 <html>
2 <head>
3 <title>
4 Netlab Reference Manual mlppak
5 </title>
6 </head>
7 <body>
8 <H1> mlppak
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Combines weights and biases into one weights vector.
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19 w = mlppak(net)
20 </PRE>
21
22
23 <p><h2>
24 Description
25 </h2>
26 <CODE>w = mlppak(net)</CODE> takes a network data structure <CODE>net</CODE> and
27 combines the component weight matrices bias vectors into a single row
28 vector <CODE>w</CODE>. The facility to switch between these two
29 representations for the network parameters is useful, for example, in
30 training a network by error function minimization, since a single
31 vector of parameters can be handled by general-purpose optimization
32 routines.
33
34 <p>The ordering of the paramters in <CODE>w</CODE> is defined by
35 <PRE>
36
37 w = [net.w1(:)', net.b1, net.w2(:)', net.b2];
38 </PRE>
39
40 where <CODE>w1</CODE> is the first-layer weight matrix, <CODE>b1</CODE> is the
41 first-layer bias vector, <CODE>w2</CODE> is the second-layer weight matrix,
42 and <CODE>b2</CODE> is the second-layer bias vector.
43
44 <p><h2>
45 See Also
46 </h2>
47 <CODE><a href="mlp.htm">mlp</a></CODE>, <CODE><a href="mlpunpak.htm">mlpunpak</a></CODE>, <CODE><a href="mlpfwd.htm">mlpfwd</a></CODE>, <CODE><a href="mlperr.htm">mlperr</a></CODE>, <CODE><a href="mlpbkp.htm">mlpbkp</a></CODE>, <CODE><a href="mlpgrad.htm">mlpgrad</a></CODE><hr>
48 <b>Pages:</b>
49 <a href="index.htm">Index</a>
50 <hr>
51 <p>Copyright (c) Ian T Nabney (1996-9)
52
53
54 </body>
55 </html>