annotate toolboxes/FullBNT-1.0.7/nethelp3.3/netpak.htm @ 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 <html>
wolffd@0 2 <head>
wolffd@0 3 <title>
wolffd@0 4 Netlab Reference Manual netpak
wolffd@0 5 </title>
wolffd@0 6 </head>
wolffd@0 7 <body>
wolffd@0 8 <H1> netpak
wolffd@0 9 </H1>
wolffd@0 10 <h2>
wolffd@0 11 Purpose
wolffd@0 12 </h2>
wolffd@0 13 Combines weights and biases into one weights vector.
wolffd@0 14
wolffd@0 15 <p><h2>
wolffd@0 16 Synopsis
wolffd@0 17 </h2>
wolffd@0 18 <PRE>
wolffd@0 19 w = netpak(net)
wolffd@0 20 </PRE>
wolffd@0 21
wolffd@0 22
wolffd@0 23 <p><h2>
wolffd@0 24 Description
wolffd@0 25 </h2>
wolffd@0 26 <CODE>w = netpak(net)</CODE> takes a network data structure <CODE>net</CODE> and
wolffd@0 27 combines the component weight matrices into a single row
wolffd@0 28 vector <CODE>w</CODE>. The facility to switch between these two
wolffd@0 29 representations for the network parameters is useful, for example, in
wolffd@0 30 training a network by error function minimization, since a single
wolffd@0 31 vector of parameters can be handled by general-purpose optimization
wolffd@0 32 routines. This function also takes into account a <CODE>mask</CODE> defined
wolffd@0 33 as a field in <CODE>net</CODE> by removing any weights that correspond to
wolffd@0 34 entries of 0 in the mask.
wolffd@0 35
wolffd@0 36 <p><h2>
wolffd@0 37 See Also
wolffd@0 38 </h2>
wolffd@0 39 <CODE><a href="net.htm">net</a></CODE>, <CODE><a href="netunpak.htm">netunpak</a></CODE>, <CODE><a href="netfwd.htm">netfwd</a></CODE>, <CODE><a href="neterr.htm">neterr</a></CODE>, <CODE><a href="netgrad.htm">netgrad</a></CODE><hr>
wolffd@0 40 <b>Pages:</b>
wolffd@0 41 <a href="index.htm">Index</a>
wolffd@0 42 <hr>
wolffd@0 43 <p>Copyright (c) Ian T Nabney (1996-9)
wolffd@0 44
wolffd@0 45
wolffd@0 46 </body>
wolffd@0 47 </html>