annotate toolboxes/FullBNT-1.0.7/nethelp3.3/mlphdotv.htm @ 0:cc4b1211e677 tip

initial commit to HG from Changeset: 646 (e263d8a21543) added further path and more save "camirversion.m"
author Daniel Wolff
date Fri, 19 Aug 2016 13:07:06 +0200
parents
children
rev   line source
Daniel@0 1 <html>
Daniel@0 2 <head>
Daniel@0 3 <title>
Daniel@0 4 Netlab Reference Manual mlphdotv
Daniel@0 5 </title>
Daniel@0 6 </head>
Daniel@0 7 <body>
Daniel@0 8 <H1> mlphdotv
Daniel@0 9 </H1>
Daniel@0 10 <h2>
Daniel@0 11 Purpose
Daniel@0 12 </h2>
Daniel@0 13 Evaluate the product of the data Hessian with a vector.
Daniel@0 14
Daniel@0 15 <p><h2>
Daniel@0 16 Synopsis
Daniel@0 17 </h2>
Daniel@0 18 <PRE>
Daniel@0 19 hdv = mlphdotv(net, x, t, v)</PRE>
Daniel@0 20
Daniel@0 21
Daniel@0 22 <p><h2>
Daniel@0 23 Description
Daniel@0 24 </h2>
Daniel@0 25
Daniel@0 26 <p><CODE>hdv = mlphdotv(net, x, t, v)</CODE> takes an MLP network data structure
Daniel@0 27 <CODE>net</CODE>, together with the matrix <CODE>x</CODE> of input vectors, the
Daniel@0 28 matrix <CODE>t</CODE> of target vectors and an arbitrary row vector <CODE>v</CODE>
Daniel@0 29 whose length equals the number of parameters in the network, and
Daniel@0 30 returns the product of the data-dependent contribution to the Hessian
Daniel@0 31 matrix with <CODE>v</CODE>. The implementation is based on the R-propagation
Daniel@0 32 algorithm of Pearlmutter.
Daniel@0 33
Daniel@0 34 <p><h2>
Daniel@0 35 See Also
Daniel@0 36 </h2>
Daniel@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>
Daniel@0 38 <b>Pages:</b>
Daniel@0 39 <a href="index.htm">Index</a>
Daniel@0 40 <hr>
Daniel@0 41 <p>Copyright (c) Ian T Nabney (1996-9)
Daniel@0 42
Daniel@0 43
Daniel@0 44 </body>
Daniel@0 45 </html>