Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mlpevfwd.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 mlpevfwd | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> mlpevfwd | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Forward propagation with evidence for MLP | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 | |
| 20 [y, extra] = mlpevfwd(net, x, t, x_test) | |
| 21 [y, extra, invhess] = mlpevfwd(net, x, t, x_test, invhess) | |
| 22 </PRE> | |
| 23 | |
| 24 | |
| 25 <p><h2> | |
| 26 Description | |
| 27 </h2> | |
| 28 <CODE>y = mlpevfwd(net, x, t, x_test)</CODE> takes a network data structure | |
| 29 <CODE>net</CODE> together with the input <CODE>x</CODE> and target <CODE>t</CODE> training data | |
| 30 and input test data <CODE>x_test</CODE>. | |
| 31 It returns the normal forward propagation through the network <CODE>y</CODE> | |
| 32 together with a matrix <CODE>extra</CODE> which consists of error bars (variance) | |
| 33 for a regression problem or moderated outputs for a classification problem. | |
| 34 The optional argument (and return value) | |
| 35 <CODE>invhess</CODE> is the inverse of the network Hessian | |
| 36 computed on the training data inputs and targets. Passing it in avoids | |
| 37 recomputing it, which can be a significant saving for large training sets. | |
| 38 | |
| 39 <p><h2> | |
| 40 See Also | |
| 41 </h2> | |
| 42 <CODE><a href="fevbayes.htm">fevbayes</a></CODE><hr> | |
| 43 <b>Pages:</b> | |
| 44 <a href="index.htm">Index</a> | |
| 45 <hr> | |
| 46 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 47 | |
| 48 | |
| 49 </body> | |
| 50 </html> |