Mercurial > hg > camir-aes2014

annotate toolboxes/FullBNT-1.0.7/nethelp3.3/mlpderiv.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
rev   line source
wolffd@0 1 <html>
wolffd@0 2 <head>
wolffd@0 3 <title>
wolffd@0 4 Netlab Reference Manual mlpderiv
wolffd@0 5 </title>
wolffd@0 6 </head>
wolffd@0 7 <body>
wolffd@0 8 <H1> mlpderiv
wolffd@0 9 </H1>
wolffd@0 10 <h2>
wolffd@0 11 Purpose
wolffd@0 12 </h2>
wolffd@0 13 Evaluate derivatives of network outputs with respect to weights.
wolffd@0 14
wolffd@0 15 <p><h2>
wolffd@0 16 Synopsis
wolffd@0 17 </h2>
wolffd@0 18 <PRE>
wolffd@0 19 g = mlpderiv(net, x)</PRE>
wolffd@0 20
wolffd@0 21
wolffd@0 22 <p><h2>
wolffd@0 23 Description
wolffd@0 24 </h2>
wolffd@0 25 <CODE>g = mlpderiv(net, x)</CODE> takes a network data structure <CODE>net</CODE>
wolffd@0 26 and a matrix of input vectors <CODE>x</CODE> and returns a three-index matrix
wolffd@0 27 <CODE>g</CODE> whose <CODE>i</CODE>, <CODE>j</CODE>, <CODE>k</CODE> element contains the
wolffd@0 28 derivative of network output <CODE>k</CODE> with respect to weight or bias
wolffd@0 29 parameter <CODE>j</CODE> for input pattern <CODE>i</CODE>. The ordering of the
wolffd@0 30 weight and bias parameters is defined by <CODE>mlpunpak</CODE>.
wolffd@0 31
wolffd@0 32 <p><h2>
wolffd@0 33 See Also
wolffd@0 34 </h2>
wolffd@0 35 <CODE><a href="mlp.htm">mlp</a></CODE>, <CODE><a href="mlppak.htm">mlppak</a></CODE>, <CODE><a href="mlpgrad.htm">mlpgrad</a></CODE>, <CODE><a href="mlpbkp.htm">mlpbkp</a></CODE><hr>
wolffd@0 36 <b>Pages:</b>
wolffd@0 37 <a href="index.htm">Index</a>
wolffd@0 38 <hr>
wolffd@0 39 <p>Copyright (c) Ian T Nabney (1996-9)
wolffd@0 40
wolffd@0 41
wolffd@0 42 </body>
wolffd@0 43 </html>