Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mdngrad.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 mdngrad | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> mdngrad | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Evaluate gradient of error function for Mixture Density Network. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 | |
| 20 g = mdngrad(net, x, t) | |
| 21 </PRE> | |
| 22 | |
| 23 | |
| 24 <p><h2> | |
| 25 Description | |
| 26 </h2> | |
| 27 | |
| 28 <CODE>g = mdngrad(net, x, t)</CODE> takes a mixture density network data | |
| 29 structure <CODE>net</CODE>, a matrix <CODE>x</CODE> of input vectors and a matrix | |
| 30 <CODE>t</CODE> of target vectors, and evaluates the gradient <CODE>g</CODE> of the | |
| 31 error function with respect to the network weights. The error function | |
| 32 is negative log likelihood of the target data. Each row of <CODE>x</CODE> | |
| 33 corresponds to one input vector and each row of <CODE>t</CODE> corresponds to | |
| 34 one target vector. | |
| 35 | |
| 36 <p><h2> | |
| 37 See Also | |
| 38 </h2> | |
| 39 <CODE><a href="mdn.htm">mdn</a></CODE>, <CODE><a href="mdnfwd.htm">mdnfwd</a></CODE>, <CODE><a href="mdnerr.htm">mdnerr</a></CODE>, <CODE><a href="mdnprob.htm">mdnprob</a></CODE>, <CODE><a href="mlpbkp.htm">mlpbkp</a></CODE><hr> | |
| 40 <b>Pages:</b> | |
| 41 <a href="index.htm">Index</a> | |
| 42 <hr> | |
| 43 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 44 <p>David J Evans (1998) | |
| 45 | |
| 46 </body> | |
| 47 </html> |