Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/rbfbkp.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
comparison
equal deleted inserted replaced
-1:000000000000 0:e9a9cd732c1e
1 <html>
2 <head>
3 <title>
4 Netlab Reference Manual rbfbkp
5 </title>
6 </head>
7 <body>
8 <H1> rbfbkp
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Backpropagate gradient of error function for RBF network.
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19 g = rbfbkp(net, x, z, n2, deltas)</PRE>
20
21
22 <p><h2>
23 Description
24 </h2>
25 <CODE>g = rbfbkp(net, x, z, n2, deltas)</CODE> takes a network data structure
26 <CODE>net</CODE> together with a matrix <CODE>x</CODE> of input vectors, a matrix
27 <CODE>z</CODE> of hidden unit activations, a matrix <CODE>n2</CODE> of the squared
28 distances between centres and inputs, and a matrix <CODE>deltas</CODE> of the
29 gradient of the error function with respect to the values of the
30 output units (i.e. the summed inputs to the output units, before the
31 activation function is applied). The return value is the gradient
32 <CODE>g</CODE> of the error function with respect to the network
33 weights. Each row of <CODE>x</CODE> corresponds to one input vector.
34
35 <p>This function is provided so that the common backpropagation algorithm
36 can be used by RBF network models to compute
37 gradients for the output values (in <CODE>rbfderiv</CODE>) as well as standard error
38 functions.
39
40 <p><h2>
41 See Also
42 </h2>
43 <CODE><a href="rbf.htm">rbf</a></CODE>, <CODE><a href="rbfgrad.htm">rbfgrad</a></CODE>, <CODE><a href="rbfderiv.htm">rbfderiv</a></CODE><hr>
44 <b>Pages:</b>
45 <a href="index.htm">Index</a>
46 <hr>
47 <p>Copyright (c) Ian T Nabney (1996-9)
48
49
50 </body>
51 </html>