Mercurial > hg > camir-ismir2012

annotate toolboxes/FullBNT-1.0.7/nethelp3.3/mlpderiv.htm @ 0:cc4b1211e677 tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
initial commit to HG from Changeset: 646 (e263d8a21543) added further path and more save "camirversion.m"
author Daniel Wolff
date Fri, 19 Aug 2016 13:07:06 +0200
parents
children
rev   line source
Daniel@0 1 <html>
Daniel@0 2 <head>
Daniel@0 3 <title>
Daniel@0 4 Netlab Reference Manual mlpderiv
Daniel@0 5 </title>
Daniel@0 6 </head>
Daniel@0 7 <body>
Daniel@0 8 <H1> mlpderiv
Daniel@0 9 </H1>
Daniel@0 10 <h2>
Daniel@0 11 Purpose
Daniel@0 12 </h2>
Daniel@0 13 Evaluate derivatives of network outputs with respect to weights.
Daniel@0 14
Daniel@0 15 <p><h2>
Daniel@0 16 Synopsis
Daniel@0 17 </h2>
Daniel@0 18 <PRE>
Daniel@0 19 g = mlpderiv(net, x)</PRE>
Daniel@0 20
Daniel@0 21
Daniel@0 22 <p><h2>
Daniel@0 23 Description
Daniel@0 24 </h2>
Daniel@0 25 <CODE>g = mlpderiv(net, x)</CODE> takes a network data structure <CODE>net</CODE>
Daniel@0 26 and a matrix of input vectors <CODE>x</CODE> and returns a three-index matrix
Daniel@0 27 <CODE>g</CODE> whose <CODE>i</CODE>, <CODE>j</CODE>, <CODE>k</CODE> element contains the
Daniel@0 28 derivative of network output <CODE>k</CODE> with respect to weight or bias
Daniel@0 29 parameter <CODE>j</CODE> for input pattern <CODE>i</CODE>. The ordering of the
Daniel@0 30 weight and bias parameters is defined by <CODE>mlpunpak</CODE>.
Daniel@0 31
Daniel@0 32 <p><h2>
Daniel@0 33 See Also
Daniel@0 34 </h2>
Daniel@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>
Daniel@0 36 <b>Pages:</b>
Daniel@0 37 <a href="index.htm">Index</a>
Daniel@0 38 <hr>
Daniel@0 39 <p>Copyright (c) Ian T Nabney (1996-9)
Daniel@0 40
Daniel@0 41
Daniel@0 42 </body>
Daniel@0 43 </html>