Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/glmderiv.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 glmderiv | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> glmderiv | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Evaluate derivatives of GLM outputs with respect to weights. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 | |
| 20 g = glmderiv(net, x) | |
| 21 </PRE> | |
| 22 | |
| 23 | |
| 24 <p><h2> | |
| 25 Description | |
| 26 </h2> | |
| 27 <CODE>g = glmderiv(net, x)</CODE> takes a network data structure <CODE>net</CODE> and a matrix | |
| 28 of input vectors <CODE>x</CODE> and returns a three-index matrix mat{g} whose | |
| 29 <CODE>i</CODE>, <CODE>j</CODE>, <CODE>k</CODE> | |
| 30 element contains the derivative of network output <CODE>k</CODE> with respect to | |
| 31 weight or bias parameter <CODE>j</CODE> for input pattern <CODE>i</CODE>. The ordering of the | |
| 32 weight and bias parameters is defined by <CODE>glmunpak</CODE>. | |
| 33 | |
| 34 <p><h2> | |
| 35 See also | |
| 36 </h2> | |
| 37 <PRE> | |
| 38 glm, glmunpak, glmgrad</PRE> | |
| 39 | |
| 40 | |
| 41 <p><hr> | |
| 42 <b>Pages:</b> | |
| 43 <a href="index.htm">Index</a> | |
| 44 <hr> | |
| 45 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 46 | |
| 47 | |
| 48 </body> | |
| 49 </html> |