annotate toolboxes/FullBNT-1.0.7/nethelp3.3/demrbf1.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 demrbf1
Daniel@0 5 </title>
Daniel@0 6 </head>
Daniel@0 7 <body>
Daniel@0 8 <H1> demrbf1
Daniel@0 9 </H1>
Daniel@0 10 <h2>
Daniel@0 11 Purpose
Daniel@0 12 </h2>
Daniel@0 13 Demonstrate simple regression using a radial basis function network.
Daniel@0 14
Daniel@0 15 <p><h2>
Daniel@0 16 Synopsis
Daniel@0 17 </h2>
Daniel@0 18 <PRE>
Daniel@0 19 demrbf1</PRE>
Daniel@0 20
Daniel@0 21
Daniel@0 22 <p><h2>
Daniel@0 23 Description
Daniel@0 24 </h2>
Daniel@0 25 The problem consists of one input variable <CODE>x</CODE> and one target variable
Daniel@0 26 <CODE>t</CODE> with data generated by sampling <CODE>x</CODE> at equal intervals and then
Daniel@0 27 generating target data by computing <CODE>sin(2*pi*x)</CODE> and adding Gaussian
Daniel@0 28 noise. This data is the same as that used in demmlp1.
Daniel@0 29
Daniel@0 30 <p>Three different RBF networks (with different activation functions)
Daniel@0 31 are trained in two stages. First, a Gaussian mixture model is trained using
Daniel@0 32 the EM algorithm, and the centres of this model are used to set the centres
Daniel@0 33 of the RBF. Second, the output weights (and biases) are determined using the
Daniel@0 34 pseudo-inverse of the design matrix.
Daniel@0 35
Daniel@0 36 <p><h2>
Daniel@0 37 See Also
Daniel@0 38 </h2>
Daniel@0 39 <CODE><a href="demmlp1.htm">demmlp1</a></CODE>, <CODE><a href="rbf.htm">rbf</a></CODE>, <CODE><a href="rbffwd.htm">rbffwd</a></CODE>, <CODE><a href="gmm.htm">gmm</a></CODE>, <CODE><a href="gmmem.htm">gmmem</a></CODE><hr>
Daniel@0 40 <b>Pages:</b>
Daniel@0 41 <a href="index.htm">Index</a>
Daniel@0 42 <hr>
Daniel@0 43 <p>Copyright (c) Ian T Nabney (1996-9)
Daniel@0 44
Daniel@0 45
Daniel@0 46 </body>
Daniel@0 47 </html>