Mercurial > hg > camir-aes2014

annotate toolboxes/FullBNT-1.0.7/nethelp3.3/mlphdotv.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 mlphdotv
wolffd@0 5 </title>
wolffd@0 6 </head>
wolffd@0 7 <body>
wolffd@0 8 <H1> mlphdotv
wolffd@0 9 </H1>
wolffd@0 10 <h2>
wolffd@0 11 Purpose
wolffd@0 12 </h2>
wolffd@0 13 Evaluate the product of the data Hessian with a vector.
wolffd@0 14
wolffd@0 15 <p><h2>
wolffd@0 16 Synopsis
wolffd@0 17 </h2>
wolffd@0 18 <PRE>
wolffd@0 19 hdv = mlphdotv(net, x, t, v)</PRE>
wolffd@0 20
wolffd@0 21
wolffd@0 22 <p><h2>
wolffd@0 23 Description
wolffd@0 24 </h2>
wolffd@0 25
wolffd@0 26 <p><CODE>hdv = mlphdotv(net, x, t, v)</CODE> takes an MLP network data structure
wolffd@0 27 <CODE>net</CODE>, together with the matrix <CODE>x</CODE> of input vectors, the
wolffd@0 28 matrix <CODE>t</CODE> of target vectors and an arbitrary row vector <CODE>v</CODE>
wolffd@0 29 whose length equals the number of parameters in the network, and
wolffd@0 30 returns the product of the data-dependent contribution to the Hessian
wolffd@0 31 matrix with <CODE>v</CODE>. The implementation is based on the R-propagation
wolffd@0 32 algorithm of Pearlmutter.
wolffd@0 33
wolffd@0 34 <p><h2>
wolffd@0 35 See Also
wolffd@0 36 </h2>
wolffd@0 37 <CODE><a href="mlp.htm">mlp</a></CODE>, <CODE><a href="mlphess.htm">mlphess</a></CODE>, <CODE><a href="hesschek.htm">hesschek</a></CODE><hr>
wolffd@0 38 <b>Pages:</b>
wolffd@0 39 <a href="index.htm">Index</a>
wolffd@0 40 <hr>
wolffd@0 41 <p>Copyright (c) Ian T Nabney (1996-9)
wolffd@0 42
wolffd@0 43
wolffd@0 44 </body>
wolffd@0 45 </html>