Mercurial > hg > camir-aes2014

annotate toolboxes/FullBNT-1.0.7/nethelp3.3/demprior.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
rev   line source
wolffd@0 1 <html>
wolffd@0 2 <head>
wolffd@0 3 <title>
wolffd@0 4 Netlab Reference Manual demprior
wolffd@0 5 </title>
wolffd@0 6 </head>
wolffd@0 7 <body>
wolffd@0 8 <H1> demprior
wolffd@0 9 </H1>
wolffd@0 10 <h2>
wolffd@0 11 Purpose
wolffd@0 12 </h2>
wolffd@0 13 Demonstrate sampling from a multi-parameter Gaussian prior.
wolffd@0 14
wolffd@0 15 <p><h2>
wolffd@0 16 Synopsis
wolffd@0 17 </h2>
wolffd@0 18 <PRE>
wolffd@0 19 demprior</PRE>
wolffd@0 20
wolffd@0 21
wolffd@0 22 <p><h2>
wolffd@0 23 Description
wolffd@0 24 </h2>
wolffd@0 25 This function plots the functions represented by a multi-layer perceptron
wolffd@0 26 network when the weights are set to values drawn from a Gaussian prior
wolffd@0 27 distribution. The parameters <CODE>aw1</CODE>, <CODE>ab1</CODE> <CODE>aw2</CODE> and <CODE>ab2</CODE>
wolffd@0 28 control the inverse variances of the first-layer weights, the hidden unit
wolffd@0 29 biases, the second-layer weights and the output unit biases respectively.
wolffd@0 30 Their values can be adjusted on a logarithmic scale using the sliders, or
wolffd@0 31 by typing values into the text boxes and pressing the return key.
wolffd@0 32
wolffd@0 33 <p><h2>
wolffd@0 34 See Also
wolffd@0 35 </h2>
wolffd@0 36 <CODE><a href="mlp.htm">mlp</a></CODE><hr>
wolffd@0 37 <b>Pages:</b>
wolffd@0 38 <a href="index.htm">Index</a>
wolffd@0 39 <hr>
wolffd@0 40 <p>Copyright (c) Ian T Nabney (1996-9)
wolffd@0 41
wolffd@0 42
wolffd@0 43 </body>
wolffd@0 44 </html>