Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/gtminit.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 gtminit
5 </title>
6 </head>
7 <body>
8 <H1> gtminit
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Initialise the weights and latent sample in a GTM.
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19 net = gtminit(net, options, data, samptype)
20 net = gtminit(net, options, data, samptype, lsampsize, rbfsampsize)
21 </PRE>
22
23
24 <p><h2>
25 Description
26 </h2>
27 <CODE>net = gtminit(net, options, data, samptype)</CODE> takes a GTM <CODE>net</CODE>
28 and generates a sample of latent data points and sets the centres (and
29 widths if appropriate) of
30 <CODE>net.rbfnet</CODE>.
31
32 <p>If the <CODE>samptype</CODE> is <CODE>'regular'</CODE>, then regular grids of latent
33 data points and RBF centres are created. The dimension of the latent data
34 space must be
35 1 or 2. For one-dimensional latent space, the <CODE>lsampsize</CODE> parameter
36 gives the number of latent points and the <CODE>rbfsampsize</CODE> parameter
37 gives the number of RBF centres. For a two-dimensional latent space,
38 these parameters must be vectors of length 2 with the number of points
39 in each of the x and y directions to create a rectangular grid. The
40 widths of the RBF basis functions are set by a call to <CODE>rbfsetfw</CODE>
41 passing <CODE>options(7)</CODE> as the scaling parameter.
42
43 <p>If the <CODE>samptype</CODE> is <CODE>'uniform'</CODE> or <CODE>'gaussian'</CODE> then the
44 latent data is found by sampling from a uniform or
45 Gaussian distribution correspondingly. The RBF basis function parameters
46 are set
47 by a call to <CODE>rbfsetbf</CODE> with the <CODE>data</CODE> parameter
48 as dataset and the <CODE>options</CODE> vector.
49
50 <p>Finally, the output layer weights of the RBF are initialised by
51 mapping the mean of the latent variable to the mean of the target variable,
52 and the L-dimensional latent variale variance to the variance of the
53 targets along the first L principal components.
54
55 <p><h2>
56 See Also
57 </h2>
58 <CODE><a href="gtm.htm">gtm</a></CODE>, <CODE><a href="gtmem.htm">gtmem</a></CODE>, <CODE><a href="pca.htm">pca</a></CODE>, <CODE><a href="rbfsetbf.htm">rbfsetbf</a></CODE>, <CODE><a href="rbfsetfw.htm">rbfsetfw</a></CODE><hr>
59 <b>Pages:</b>
60 <a href="index.htm">Index</a>
61 <hr>
62 <p>Copyright (c) Ian T Nabney (1996-9)
63
64
65 </body>
66 </html>