Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/gp.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 gp
5 </title>
6 </head>
7 <body>
8 <H1> gp
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Create a Gaussian Process.
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19 net = gp(nin, covarfn)
20 net = gp(nin, covarfn, prior)
21 </PRE>
22
23
24 <p><h2>
25 Description
26 </h2>
27
28 <p><CODE>net = gp(nin, covarfn)</CODE> takes the number of inputs <CODE>nin</CODE>
29 for a Gaussian Process model with a single output, together
30 with a string <CODE>covarfn</CODE> which specifies the type of the covariance function,
31 and returns a data structure <CODE>net</CODE>. The parameters are set to zero.
32
33 <p>The fields in <CODE>net</CODE> are
34 <PRE>
35 type = 'gp'
36 nin = number of inputs
37 nout = number of outputs: always 1
38 nwts = total number of weights and covariance function parameters
39 bias = logarithm of constant offset in covariance function
40 noise = logarithm of output noise variance
41 inweights = logarithm of inverse length scale for each input
42 covarfn = string describing the covariance function:
43 'sqexp'
44 'ratquad'
45 fpar = covariance function specific parameters (1 for squared exponential,
46 2 for rational quadratic)
47 trin = training input data (initially empty)
48 trtargets = training target data (initially empty)
49 </PRE>
50
51
52 <p><CODE>net = gp(nin, covarfn, prior)</CODE> sets a Gaussian prior on the
53 parameters of the model. <CODE>prior</CODE> must contain the fields
54 <CODE>pr_mean</CODE> and <CODE>pr_variance</CODE>. If <CODE>pr_mean</CODE> is a scalar,
55 then the Gaussian is assumed to be isotropic and the additional fields
56 <CODE>net.pr_mean</CODE> and <CODE>pr_variance</CODE> are set. Otherwise,
57 the Gaussian prior has a mean
58 defined by a column vector of parameters <CODE>prior.pr_mean</CODE> and
59 covariance defined by a column vector of parameters <CODE>prior.pr_variance</CODE>.
60 Each element of <CODE>prmean</CODE> corresponds to a separate group of parameters, which
61 need not be mutually exclusive. The membership of the groups is defined
62 by the matrix <CODE>prior.index</CODE> in which the columns correspond to the elements of
63 <CODE>prmean</CODE>. Each column has one element for each weight in the matrix,
64 in the order defined by the function <CODE>gppak</CODE>, and each element
65 is 1 or 0 according to whether the parameter is a member of the
66 corresponding group or not. The additional field <CODE>net.index</CODE> is set
67 in this case.
68
69 <p><h2>
70 See Also
71 </h2>
72 <CODE><a href="gppak.htm">gppak</a></CODE>, <CODE><a href="gpunpak.htm">gpunpak</a></CODE>, <CODE><a href="gpfwd.htm">gpfwd</a></CODE>, <CODE><a href="gperr.htm">gperr</a></CODE>, <CODE><a href="gpcovar.htm">gpcovar</a></CODE>, <CODE><a href="gpgrad.htm">gpgrad</a></CODE><hr>
73 <b>Pages:</b>
74 <a href="index.htm">Index</a>
75 <hr>
76 <p>Copyright (c) Ian T Nabney (1996-9)
77
78
79 </body>
80 </html>