Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mdninit.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
comparison
equal deleted inserted replaced
-1:000000000000 0:e9a9cd732c1e
1 <html>
2 <head>
3 <title>
4 Netlab Reference Manual mdninit
5 </title>
6 </head>
7 <body>
8 <H1> mdninit
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Initialise the weights in a Mixture Density Network.
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19 net = mdninit(net, prior)
20 net = mdninit(net, prior, t, options)
21 </PRE>
22
23
24 <p><h2>
25 Description
26 </h2>
27
28 <p><CODE>net = mdninit(net, prior)</CODE> takes a Mixture Density Network
29 <CODE>net</CODE> and sets the weights and biases by sampling from a Gaussian
30 distribution. It calls <CODE>mlpinit</CODE> for the MLP component of <CODE>net</CODE>.
31
32 <p><CODE>net = mdninit(net, prior, t, options)</CODE> uses the target data <CODE>t</CODE> to
33 initialise the biases for the output units after initialising the
34 other weights as above. It calls <CODE>gmminit</CODE>, with <CODE>t</CODE> and <CODE>options</CODE>
35 as arguments, to obtain a model of the unconditional density of <CODE>t</CODE>. The
36 biases are then set so that <CODE>net</CODE> will output the values in the Gaussian
37 mixture model.
38
39 <p><h2>
40 See Also
41 </h2>
42 <CODE><a href="mdn.htm">mdn</a></CODE>, <CODE><a href="mlp.htm">mlp</a></CODE>, <CODE><a href="mlpinit.htm">mlpinit</a></CODE>, <CODE><a href="gmminit.htm">gmminit</a></CODE><hr>
43 <b>Pages:</b>
44 <a href="index.htm">Index</a>
45 <hr>
46 <p>Copyright (c) Ian T Nabney (1996-9)
47 <p>David J Evans (1998)
48
49 </body>
50 </html>