annotate toolboxes/FullBNT-1.0.7/nethelp3.3/gmminit.htm @ 0:cc4b1211e677 tip

initial commit to HG from Changeset: 646 (e263d8a21543) added further path and more save "camirversion.m"
author Daniel Wolff
date Fri, 19 Aug 2016 13:07:06 +0200
parents
children
rev   line source
Daniel@0 1 <html>
Daniel@0 2 <head>
Daniel@0 3 <title>
Daniel@0 4 Netlab Reference Manual gmminit
Daniel@0 5 </title>
Daniel@0 6 </head>
Daniel@0 7 <body>
Daniel@0 8 <H1> gmminit
Daniel@0 9 </H1>
Daniel@0 10 <h2>
Daniel@0 11 Purpose
Daniel@0 12 </h2>
Daniel@0 13 Initialises Gaussian mixture model from data
Daniel@0 14
Daniel@0 15 <p><h2>
Daniel@0 16 Synopsis
Daniel@0 17 </h2>
Daniel@0 18 <PRE>
Daniel@0 19
Daniel@0 20 mix = gmminit(mix, x, options)
Daniel@0 21 </PRE>
Daniel@0 22
Daniel@0 23
Daniel@0 24 <p><h2>
Daniel@0 25 Description
Daniel@0 26 </h2>
Daniel@0 27 <CODE>mix = gmminit(mix, x, options)</CODE> uses a dataset <CODE>x</CODE>
Daniel@0 28 to initialise the parameters of a Gaussian mixture
Daniel@0 29 model defined by the data structure <CODE>mix</CODE>. The k-means algorithm
Daniel@0 30 is used to determine the centres. The priors are computed from the
Daniel@0 31 proportion of examples belonging to each cluster.
Daniel@0 32 The covariance matrices are calculated as the sample covariance of the
Daniel@0 33 points associated with (i.e. closest to) the corresponding centres.
Daniel@0 34 For a mixture of PPCA model, the PPCA decomposition is calculated
Daniel@0 35 for the points closest to a given centre.
Daniel@0 36 This initialisation can be used as the starting point for training the
Daniel@0 37 model using the EM algorithm.
Daniel@0 38
Daniel@0 39 <p><h2>
Daniel@0 40 Example
Daniel@0 41 </h2>
Daniel@0 42 <PRE>
Daniel@0 43
Daniel@0 44 mix = gmm(3, 2);
Daniel@0 45 options = foptions;
Daniel@0 46 options(14) = 5;
Daniel@0 47 mix = gmminit(mix, data, options);
Daniel@0 48 </PRE>
Daniel@0 49
Daniel@0 50 This code sets up a Gaussian mixture model with 3 centres in 2 dimensions, and
Daniel@0 51 then initialises the parameters from the data set <CODE>data</CODE> with 5 iterations
Daniel@0 52 of the k means algorithm.
Daniel@0 53
Daniel@0 54 <p><h2>
Daniel@0 55 See Also
Daniel@0 56 </h2>
Daniel@0 57 <CODE><a href="gmm.htm">gmm</a></CODE><hr>
Daniel@0 58 <b>Pages:</b>
Daniel@0 59 <a href="index.htm">Index</a>
Daniel@0 60 <hr>
Daniel@0 61 <p>Copyright (c) Ian T Nabney (1996-9)
Daniel@0 62
Daniel@0 63
Daniel@0 64 </body>
Daniel@0 65 </html>