Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mlpinit.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 mlpinit | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> mlpinit | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Initialise the weights in a 2-layer feedforward network. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 net = mlpinit(net, prior) | |
| 20 </PRE> | |
| 21 | |
| 22 | |
| 23 <p><h2> | |
| 24 Description | |
| 25 </h2> | |
| 26 | |
| 27 <p><CODE>net = mlpinit(net, prior)</CODE> takes a 2-layer feedforward network | |
| 28 <CODE>net</CODE> and sets the weights and biases by sampling from a Gaussian | |
| 29 distribution. If <CODE>prior</CODE> is a scalar, then all of the parameters | |
| 30 (weights and biases) are sampled from a single isotropic Gaussian with | |
| 31 inverse variance equal to <CODE>prior</CODE>. If <CODE>prior</CODE> is a data | |
| 32 structure of the kind generated by <CODE>mlpprior</CODE>, then the parameters | |
| 33 are sampled from multiple Gaussians according to their groupings | |
| 34 (defined by the <CODE>index</CODE> field) with corresponding variances | |
| 35 (defined by the <CODE>alpha</CODE> field). | |
| 36 | |
| 37 <p><h2> | |
| 38 See Also | |
| 39 </h2> | |
| 40 <CODE><a href="mlp.htm">mlp</a></CODE>, <CODE><a href="mlpprior.htm">mlpprior</a></CODE>, <CODE><a href="mlppak.htm">mlppak</a></CODE>, <CODE><a href="mlpunpak.htm">mlpunpak</a></CODE><hr> | |
| 41 <b>Pages:</b> | |
| 42 <a href="index.htm">Index</a> | |
| 43 <hr> | |
| 44 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 45 | |
| 46 | |
| 47 </body> | |
| 48 </html> |