annotate toolboxes/FullBNT-1.0.7/nethelp3.3/rbfgrad.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 rbfgrad
wolffd@0 5 </title>
wolffd@0 6 </head>
wolffd@0 7 <body>
wolffd@0 8 <H1> rbfgrad
wolffd@0 9 </H1>
wolffd@0 10 <h2>
wolffd@0 11 Purpose
wolffd@0 12 </h2>
wolffd@0 13 Evaluate gradient of error function for RBF network.
wolffd@0 14
wolffd@0 15 <p><h2>
wolffd@0 16 Synopsis
wolffd@0 17 </h2>
wolffd@0 18 <PRE>
wolffd@0 19
wolffd@0 20 g = rbfgrad(net, x, t)
wolffd@0 21 [g, gdata, gprior] = rbfgrad(net, x, t)
wolffd@0 22 </PRE>
wolffd@0 23
wolffd@0 24
wolffd@0 25 <p><h2>
wolffd@0 26 Description
wolffd@0 27 </h2>
wolffd@0 28 <CODE>g = rbfgrad(net, x, t)</CODE> takes a network data structure <CODE>net</CODE>
wolffd@0 29 together with a matrix <CODE>x</CODE> of input
wolffd@0 30 vectors and a matrix <CODE>t</CODE> of target vectors, and evaluates the gradient
wolffd@0 31 <CODE>g</CODE> of the error function with respect to the network weights (i.e.
wolffd@0 32 including the hidden unit parameters). The error
wolffd@0 33 function is sum of squares.
wolffd@0 34 Each row of <CODE>x</CODE> corresponds to one
wolffd@0 35 input vector and each row of <CODE>t</CODE> contains the corresponding target vector.
wolffd@0 36 If the output function is <CODE>'neuroscale'</CODE> then the gradient is only
wolffd@0 37 computed for the output layer weights and biases.
wolffd@0 38
wolffd@0 39 <p><CODE>[g, gdata, gprior] = rbfgrad(net, x, t)</CODE> also returns separately
wolffd@0 40 the data and prior contributions to the gradient. In the case of
wolffd@0 41 multiple groups in the prior, <CODE>gprior</CODE> is a matrix with a row
wolffd@0 42 for each group and a column for each weight parameter.
wolffd@0 43
wolffd@0 44 <p><h2>
wolffd@0 45 See Also
wolffd@0 46 </h2>
wolffd@0 47 <CODE><a href="rbf.htm">rbf</a></CODE>, <CODE><a href="rbffwd.htm">rbffwd</a></CODE>, <CODE><a href="rbferr.htm">rbferr</a></CODE>, <CODE><a href="rbfpak.htm">rbfpak</a></CODE>, <CODE><a href="rbfunpak.htm">rbfunpak</a></CODE>, <CODE><a href="rbfbkp.htm">rbfbkp</a></CODE><hr>
wolffd@0 48 <b>Pages:</b>
wolffd@0 49 <a href="index.htm">Index</a>
wolffd@0 50 <hr>
wolffd@0 51 <p>Copyright (c) Ian T Nabney (1996-9)
wolffd@0 52
wolffd@0 53
wolffd@0 54 </body>
wolffd@0 55 </html>