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

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 mdngrad
Daniel@0 5 </title>
Daniel@0 6 </head>
Daniel@0 7 <body>
Daniel@0 8 <H1> mdngrad
Daniel@0 9 </H1>
Daniel@0 10 <h2>
Daniel@0 11 Purpose
Daniel@0 12 </h2>
Daniel@0 13 Evaluate gradient of error function for Mixture Density Network.
Daniel@0 14
Daniel@0 15 <p><h2>
Daniel@0 16 Synopsis
Daniel@0 17 </h2>
Daniel@0 18 <PRE>
Daniel@0 19
Daniel@0 20 g = mdngrad(net, x, t)
Daniel@0 21 </PRE>
Daniel@0 22
Daniel@0 23
Daniel@0 24 <p><h2>
Daniel@0 25 Description
Daniel@0 26 </h2>
Daniel@0 27
Daniel@0 28 <CODE>g = mdngrad(net, x, t)</CODE> takes a mixture density network data
Daniel@0 29 structure <CODE>net</CODE>, a matrix <CODE>x</CODE> of input vectors and a matrix
Daniel@0 30 <CODE>t</CODE> of target vectors, and evaluates the gradient <CODE>g</CODE> of the
Daniel@0 31 error function with respect to the network weights. The error function
Daniel@0 32 is negative log likelihood of the target data. Each row of <CODE>x</CODE>
Daniel@0 33 corresponds to one input vector and each row of <CODE>t</CODE> corresponds to
Daniel@0 34 one target vector.
Daniel@0 35
Daniel@0 36 <p><h2>
Daniel@0 37 See Also
Daniel@0 38 </h2>
Daniel@0 39 <CODE><a href="mdn.htm">mdn</a></CODE>, <CODE><a href="mdnfwd.htm">mdnfwd</a></CODE>, <CODE><a href="mdnerr.htm">mdnerr</a></CODE>, <CODE><a href="mdnprob.htm">mdnprob</a></CODE>, <CODE><a href="mlpbkp.htm">mlpbkp</a></CODE><hr>
Daniel@0 40 <b>Pages:</b>
Daniel@0 41 <a href="index.htm">Index</a>
Daniel@0 42 <hr>
Daniel@0 43 <p>Copyright (c) Ian T Nabney (1996-9)
Daniel@0 44 <p>David J Evans (1998)
Daniel@0 45
Daniel@0 46 </body>
Daniel@0 47 </html>