annotate toolboxes/FullBNT-1.0.7/nethelp3.3/demprior.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 demprior
Daniel@0 5 </title>
Daniel@0 6 </head>
Daniel@0 7 <body>
Daniel@0 8 <H1> demprior
Daniel@0 9 </H1>
Daniel@0 10 <h2>
Daniel@0 11 Purpose
Daniel@0 12 </h2>
Daniel@0 13 Demonstrate sampling from a multi-parameter Gaussian prior.
Daniel@0 14
Daniel@0 15 <p><h2>
Daniel@0 16 Synopsis
Daniel@0 17 </h2>
Daniel@0 18 <PRE>
Daniel@0 19 demprior</PRE>
Daniel@0 20
Daniel@0 21
Daniel@0 22 <p><h2>
Daniel@0 23 Description
Daniel@0 24 </h2>
Daniel@0 25 This function plots the functions represented by a multi-layer perceptron
Daniel@0 26 network when the weights are set to values drawn from a Gaussian prior
Daniel@0 27 distribution. The parameters <CODE>aw1</CODE>, <CODE>ab1</CODE> <CODE>aw2</CODE> and <CODE>ab2</CODE>
Daniel@0 28 control the inverse variances of the first-layer weights, the hidden unit
Daniel@0 29 biases, the second-layer weights and the output unit biases respectively.
Daniel@0 30 Their values can be adjusted on a logarithmic scale using the sliders, or
Daniel@0 31 by typing values into the text boxes and pressing the return key.
Daniel@0 32
Daniel@0 33 <p><h2>
Daniel@0 34 See Also
Daniel@0 35 </h2>
Daniel@0 36 <CODE><a href="mlp.htm">mlp</a></CODE><hr>
Daniel@0 37 <b>Pages:</b>
Daniel@0 38 <a href="index.htm">Index</a>
Daniel@0 39 <hr>
Daniel@0 40 <p>Copyright (c) Ian T Nabney (1996-9)
Daniel@0 41
Daniel@0 42
Daniel@0 43 </body>
Daniel@0 44 </html>