annotate toolboxes/FullBNT-1.0.7/nethelp3.3/mlpderiv.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 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>