Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/netderiv.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 netderiv | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> netderiv | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Evaluate derivatives of network outputs by weights generically. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 g = netderiv(w, net, x)</PRE> | |
| 20 | |
| 21 | |
| 22 <p><h2> | |
| 23 Description | |
| 24 </h2> | |
| 25 | |
| 26 <p><CODE>g = netderiv(w, net, x)</CODE> takes a weight vector <CODE>w</CODE> and a network | |
| 27 data structure <CODE>net</CODE>, together with the matrix <CODE>x</CODE> of input | |
| 28 vectors, and returns the | |
| 29 gradient of the outputs with respect to the weights evaluated at <CODE>w</CODE>. | |
| 30 | |
| 31 <p><h2> | |
| 32 See Also | |
| 33 </h2> | |
| 34 <CODE><a href="netevfwd.htm">netevfwd</a></CODE>, <CODE><a href="netopt.htm">netopt</a></CODE><hr> | |
| 35 <b>Pages:</b> | |
| 36 <a href="index.htm">Index</a> | |
| 37 <hr> | |
| 38 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 39 | |
| 40 | |
| 41 </body> | |
| 42 </html> |