Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/gtm.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 gtm | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> gtm | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Create a Generative Topographic Map. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc) | |
| 20 net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc, prior) | |
| 21 </PRE> | |
| 22 | |
| 23 | |
| 24 <p><h2> | |
| 25 Description | |
| 26 </h2> | |
| 27 | |
| 28 <p><CODE>net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc)</CODE>, | |
| 29 takes the dimension of the latent space <CODE>dimlatent</CODE>, the | |
| 30 number of data points sampled in the latent space <CODE>nlatent</CODE>, the | |
| 31 dimension of the data space <CODE>dimdata</CODE>, the number of centres in the | |
| 32 RBF model <CODE>ncentres</CODE>, the activation function for the RBF | |
| 33 <CODE>rbfunc</CODE> | |
| 34 and returns a data structure <CODE>net</CODE>. The parameters in the | |
| 35 RBF and GMM sub-models are set by calls to the corresponding creation routines | |
| 36 <CODE>rbf</CODE> and <CODE>gmm</CODE>. | |
| 37 | |
| 38 <p>The fields in <CODE>net</CODE> are | |
| 39 <PRE> | |
| 40 type = 'gtm' | |
| 41 nin = dimension of data space | |
| 42 dimlatent = dimension of latent space | |
| 43 rbfnet = RBF network data structure | |
| 44 gmmnet = GMM data structure | |
| 45 X = sample of latent points | |
| 46 </PRE> | |
| 47 | |
| 48 | |
| 49 <p><CODE>net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc, prior)</CODE>, | |
| 50 sets a Gaussian zero mean prior on the | |
| 51 parameters of the RBF model. <CODE>prior</CODE> must be a scalar and represents | |
| 52 the inverse variance of the prior distribution. This gives rise to | |
| 53 a weight decay term in the error function. | |
| 54 | |
| 55 <p><h2> | |
| 56 See Also | |
| 57 </h2> | |
| 58 <CODE><a href="gtmfwd.htm">gtmfwd</a></CODE>, <CODE><a href="gtmpost.htm">gtmpost</a></CODE>, <CODE><a href="rbf.htm">rbf</a></CODE>, <CODE><a href="gmm.htm">gmm</a></CODE><hr> | |
| 59 <b>Pages:</b> | |
| 60 <a href="index.htm">Index</a> | |
| 61 <hr> | |
| 62 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 63 | |
| 64 | |
| 65 </body> | |
| 66 </html> |