annotate toolboxes/FullBNT-1.0.7/nethelp3.3/demev3.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 demev3
Daniel@0 5 </title>
Daniel@0 6 </head>
Daniel@0 7 <body>
Daniel@0 8 <H1> demev3
Daniel@0 9 </H1>
Daniel@0 10 <h2>
Daniel@0 11 Purpose
Daniel@0 12 </h2>
Daniel@0 13 Demonstrate Bayesian regression for the RBF.
Daniel@0 14
Daniel@0 15 <p><h2>
Daniel@0 16 Synopsis
Daniel@0 17 </h2>
Daniel@0 18 <PRE>
Daniel@0 19 demev3</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 an input variable <CODE>x</CODE> which sampled from a
Daniel@0 26 Gaussian distribution, and a target variable <CODE>t</CODE> generated by
Daniel@0 27 computing <CODE>sin(2*pi*x)</CODE> and adding Gaussian noise. An RBF
Daniel@0 28 network with linear outputs is trained by minimizing a sum-of-squares
Daniel@0 29 error function with isotropic Gaussian regularizer, using the scaled
Daniel@0 30 conjugate gradient optimizer. The hyperparameters <CODE>alpha</CODE> and
Daniel@0 31 <CODE>beta</CODE> are re-estimated using the function <CODE>evidence</CODE>. A graph
Daniel@0 32 is plotted of the original function, the training data, the trained
Daniel@0 33 network function, and the error bars.
Daniel@0 34
Daniel@0 35 <p><h2>
Daniel@0 36 See Also
Daniel@0 37 </h2>
Daniel@0 38 <CODE><a href="demev1.htm">demev1</a></CODE>, <CODE><a href="evidence.htm">evidence</a></CODE>, <CODE><a href="rbf.htm">rbf</a></CODE>, <CODE><a href="scg.htm">scg</a></CODE>, <CODE><a href="netevfwd.htm">netevfwd</a></CODE><hr>
Daniel@0 39 <b>Pages:</b>
Daniel@0 40 <a href="index.htm">Index</a>
Daniel@0 41 <hr>
Daniel@0 42 <p>Copyright (c) Ian T Nabney (1996-9)
Daniel@0 43
Daniel@0 44
Daniel@0 45 </body>
Daniel@0 46 </html>