Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mlpgrad.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 mlpgrad
5 </title>
6 </head>
7 <body>
8 <H1> mlpgrad
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Evaluate gradient of error function for 2-layer network.
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19
20 g = mlpgrad(net, x, t)
21 </PRE>
22
23
24 <p><h2>
25 Description
26 </h2>
27 <CODE>g = mlpgrad(net, x, t)</CODE> takes a network data structure <CODE>net</CODE>
28 together with a matrix <CODE>x</CODE> of input vectors and a matrix <CODE>t</CODE>
29 of target vectors, and evaluates the gradient <CODE>g</CODE> of the error
30 function with respect to the network weights. The error funcion
31 corresponds to the choice of output unit activation function. Each row
32 of <CODE>x</CODE> corresponds to one input vector and each row of <CODE>t</CODE>
33 corresponds to one target vector.
34
35 <p><CODE>[g, gdata, gprior] = mlpgrad(net, x, t)</CODE> also returns separately
36 the data and prior contributions to the gradient. In the case of
37 multiple groups in the prior, <CODE>gprior</CODE> is a matrix with a row
38 for each group and a column for each weight parameter.
39
40 <p><h2>
41 See Also
42 </h2>
43 <CODE><a href="mlp.htm">mlp</a></CODE>, <CODE><a href="mlppak.htm">mlppak</a></CODE>, <CODE><a href="mlpunpak.htm">mlpunpak</a></CODE>, <CODE><a href="mlpfwd.htm">mlpfwd</a></CODE>, <CODE><a href="mlperr.htm">mlperr</a></CODE>, <CODE><a href="mlpbkp.htm">mlpbkp</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>