Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/demprior.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 demprior | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> demprior | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Demonstrate sampling from a multi-parameter Gaussian prior. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 demprior</PRE> | |
| 20 | |
| 21 | |
| 22 <p><h2> | |
| 23 Description | |
| 24 </h2> | |
| 25 This function plots the functions represented by a multi-layer perceptron | |
| 26 network when the weights are set to values drawn from a Gaussian prior | |
| 27 distribution. The parameters <CODE>aw1</CODE>, <CODE>ab1</CODE> <CODE>aw2</CODE> and <CODE>ab2</CODE> | |
| 28 control the inverse variances of the first-layer weights, the hidden unit | |
| 29 biases, the second-layer weights and the output unit biases respectively. | |
| 30 Their values can be adjusted on a logarithmic scale using the sliders, or | |
| 31 by typing values into the text boxes and pressing the return key. | |
| 32 | |
| 33 <p><h2> | |
| 34 See Also | |
| 35 </h2> | |
| 36 <CODE><a href="mlp.htm">mlp</a></CODE><hr> | |
| 37 <b>Pages:</b> | |
| 38 <a href="index.htm">Index</a> | |
| 39 <hr> | |
| 40 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 41 | |
| 42 | |
| 43 </body> | |
| 44 </html> |