Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/gmminit.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 gmminit
5 </title>
6 </head>
7 <body>
8 <H1> gmminit
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Initialises Gaussian mixture model from data
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19
20 mix = gmminit(mix, x, options)
21 </PRE>
22
23
24 <p><h2>
25 Description
26 </h2>
27 <CODE>mix = gmminit(mix, x, options)</CODE> uses a dataset <CODE>x</CODE>
28 to initialise the parameters of a Gaussian mixture
29 model defined by the data structure <CODE>mix</CODE>. The k-means algorithm
30 is used to determine the centres. The priors are computed from the
31 proportion of examples belonging to each cluster.
32 The covariance matrices are calculated as the sample covariance of the
33 points associated with (i.e. closest to) the corresponding centres.
34 For a mixture of PPCA model, the PPCA decomposition is calculated
35 for the points closest to a given centre.
36 This initialisation can be used as the starting point for training the
37 model using the EM algorithm.
38
39 <p><h2>
40 Example
41 </h2>
42 <PRE>
43
44 mix = gmm(3, 2);
45 options = foptions;
46 options(14) = 5;
47 mix = gmminit(mix, data, options);
48 </PRE>
49
50 This code sets up a Gaussian mixture model with 3 centres in 2 dimensions, and
51 then initialises the parameters from the data set <CODE>data</CODE> with 5 iterations
52 of the k means algorithm.
53
54 <p><h2>
55 See Also
56 </h2>
57 <CODE><a href="gmm.htm">gmm</a></CODE><hr>
58 <b>Pages:</b>
59 <a href="index.htm">Index</a>
60 <hr>
61 <p>Copyright (c) Ian T Nabney (1996-9)
62
63
64 </body>
65 </html>