Mercurial > hg > camir-aes2014

comparison toolboxes/FullBNT-1.0.7/nethelp3.3/netevfwd.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 netevfwd
5 </title>
6 </head>
7 <body>
8 <H1> netevfwd
9 </H1>
10 <h2>
11 Purpose
12 </h2>
13 Generic forward propagation with evidence for network
14
15 <p><h2>
16 Synopsis
17 </h2>
18 <PRE>
19
20 [y, extra] = netevfwd(w, net, x, t, x_test)
21 [y, extra, invhess] = netevfwd(w, net, x, t, x_test, invhess)
22 </PRE>
23
24
25 <p><h2>
26 Description
27 </h2>
28 <CODE>[y, extra] = netevfwd(w, net, x, t, x_test)</CODE> takes a network data
29 structure
30 <CODE>net</CODE> together with the input <CODE>x</CODE> and target <CODE>t</CODE> training data
31 and input test data <CODE>x_test</CODE>.
32 It returns the normal forward propagation through the network <CODE>y</CODE>
33 together with a matrix <CODE>extra</CODE> which consists of error bars (variance)
34 for a regression problem or moderated outputs for a classification problem.
35
36 <p>The optional argument (and return value)
37 <CODE>invhess</CODE> is the inverse of the network Hessian
38 computed on the training data inputs and targets. Passing it in avoids
39 recomputing it, which can be a significant saving for large training sets.
40
41 <p><h2>
42 See Also
43 </h2>
44 <CODE><a href="mlpevfwd.htm">mlpevfwd</a></CODE>, <CODE><a href="rbfevfwd.htm">rbfevfwd</a></CODE>, <CODE><a href="glmevfwd.htm">glmevfwd</a></CODE>, <CODE><a href="fevbayes.htm">fevbayes</a></CODE><hr>
45 <b>Pages:</b>
46 <a href="index.htm">Index</a>
47 <hr>
48 <p>Copyright (c) Ian T Nabney (1996-9)
49
50
51 </body>
52 </html>