Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mlphdotv.htm @ 0:e9a9cd732c1e tip
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 mlphdotv | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> mlphdotv | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Evaluate the product of the data Hessian with a vector. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 hdv = mlphdotv(net, x, t, v)</PRE> | |
| 20 | |
| 21 | |
| 22 <p><h2> | |
| 23 Description | |
| 24 </h2> | |
| 25 | |
| 26 <p><CODE>hdv = mlphdotv(net, x, t, v)</CODE> takes an MLP network data structure | |
| 27 <CODE>net</CODE>, together with the matrix <CODE>x</CODE> of input vectors, the | |
| 28 matrix <CODE>t</CODE> of target vectors and an arbitrary row vector <CODE>v</CODE> | |
| 29 whose length equals the number of parameters in the network, and | |
| 30 returns the product of the data-dependent contribution to the Hessian | |
| 31 matrix with <CODE>v</CODE>. The implementation is based on the R-propagation | |
| 32 algorithm of Pearlmutter. | |
| 33 | |
| 34 <p><h2> | |
| 35 See Also | |
| 36 </h2> | |
| 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> | |
| 38 <b>Pages:</b> | |
| 39 <a href="index.htm">Index</a> | |
| 40 <hr> | |
| 41 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 42 | |
| 43 | |
| 44 </body> | |
| 45 </html> |