Mercurial > hg > camir-ismir2012
annotate toolboxes/FullBNT-1.0.7/nethelp3.3/netevfwd.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 netevfwd |
| Daniel@0 | 5 </title> |
| Daniel@0 | 6 </head> |
| Daniel@0 | 7 <body> |
| Daniel@0 | 8 <H1> netevfwd |
| Daniel@0 | 9 </H1> |
| Daniel@0 | 10 <h2> |
| Daniel@0 | 11 Purpose |
| Daniel@0 | 12 </h2> |
| Daniel@0 | 13 Generic forward propagation with evidence for network |
| Daniel@0 | 14 |
| Daniel@0 | 15 <p><h2> |
| Daniel@0 | 16 Synopsis |
| Daniel@0 | 17 </h2> |
| Daniel@0 | 18 <PRE> |
| Daniel@0 | 19 |
| Daniel@0 | 20 [y, extra] = netevfwd(w, net, x, t, x_test) |
| Daniel@0 | 21 [y, extra, invhess] = netevfwd(w, net, x, t, x_test, invhess) |
| Daniel@0 | 22 </PRE> |
| Daniel@0 | 23 |
| Daniel@0 | 24 |
| Daniel@0 | 25 <p><h2> |
| Daniel@0 | 26 Description |
| Daniel@0 | 27 </h2> |
| Daniel@0 | 28 <CODE>[y, extra] = netevfwd(w, net, x, t, x_test)</CODE> takes a network data |
| Daniel@0 | 29 structure |
| Daniel@0 | 30 <CODE>net</CODE> together with the input <CODE>x</CODE> and target <CODE>t</CODE> training data |
| Daniel@0 | 31 and input test data <CODE>x_test</CODE>. |
| Daniel@0 | 32 It returns the normal forward propagation through the network <CODE>y</CODE> |
| Daniel@0 | 33 together with a matrix <CODE>extra</CODE> which consists of error bars (variance) |
| Daniel@0 | 34 for a regression problem or moderated outputs for a classification problem. |
| Daniel@0 | 35 |
| Daniel@0 | 36 <p>The optional argument (and return value) |
| Daniel@0 | 37 <CODE>invhess</CODE> is the inverse of the network Hessian |
| Daniel@0 | 38 computed on the training data inputs and targets. Passing it in avoids |
| Daniel@0 | 39 recomputing it, which can be a significant saving for large training sets. |
| Daniel@0 | 40 |
| Daniel@0 | 41 <p><h2> |
| Daniel@0 | 42 See Also |
| Daniel@0 | 43 </h2> |
| Daniel@0 | 44 <CODE><a href="mlpevfwd.htm">mlpevfwd</a></CODE>, <CODE><a href="rbfevfwd.htm">rbfevfwd</a></CODE>, <CODE><a href="glmevfwd.htm">glmevfwd</a></CODE>, <CODE><a href="fevbayes.htm">fevbayes</a></CODE><hr> |
| Daniel@0 | 45 <b>Pages:</b> |
| Daniel@0 | 46 <a href="index.htm">Index</a> |
| Daniel@0 | 47 <hr> |
| Daniel@0 | 48 <p>Copyright (c) Ian T Nabney (1996-9) |
| Daniel@0 | 49 |
| Daniel@0 | 50 |
| Daniel@0 | 51 </body> |
| Daniel@0 | 52 </html> |