Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/nethelp3.3/mdnfwd.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 mdnfwd | |
| 5 </title> | |
| 6 </head> | |
| 7 <body> | |
| 8 <H1> mdnfwd | |
| 9 </H1> | |
| 10 <h2> | |
| 11 Purpose | |
| 12 </h2> | |
| 13 Forward propagation through Mixture Density Network. | |
| 14 | |
| 15 <p><h2> | |
| 16 Synopsis | |
| 17 </h2> | |
| 18 <PRE> | |
| 19 mixparams = mdnfwd(net, x) | |
| 20 [mixparams, y, z] = mdnfwd(net, x) | |
| 21 [mixparams, y, z, a] = mdnfwd(net, x) | |
| 22 </PRE> | |
| 23 | |
| 24 | |
| 25 <p><h2> | |
| 26 Description | |
| 27 </h2> | |
| 28 | |
| 29 <CODE>mixparams = mdnfwd(net, x)</CODE> takes a mixture density network data | |
| 30 structure <CODE>net</CODE> and a matrix <CODE>x</CODE> of input vectors, and forward | |
| 31 propagates the inputs through the network to generate a structure | |
| 32 <CODE>mixparams</CODE> which contains the parameters of several mixture models. | |
| 33 Each row of <CODE>x</CODE> represents | |
| 34 one input vector and the corresponding row of the matrices in <CODE>mixparams</CODE> | |
| 35 represents the parameters of a mixture model for the conditional probability | |
| 36 of target vectors given the input vector. This is not represented as an array | |
| 37 of <CODE>gmm</CODE> structures to improve the efficiency of MDN training. | |
| 38 | |
| 39 <p>The fields in <CODE>mixparams</CODE> are | |
| 40 <PRE> | |
| 41 | |
| 42 type = 'mdnmixes' | |
| 43 ncentres = number of mixture components | |
| 44 dimtarget = dimension of target space | |
| 45 mixcoeffs = mixing coefficients | |
| 46 centres = means of Gaussians: stored as one row per pattern | |
| 47 covars = covariances of Gaussians | |
| 48 nparams = number of parameters | |
| 49 </PRE> | |
| 50 | |
| 51 | |
| 52 <p><CODE>[mixparams, y, z] = mdnfwd(net, x)</CODE> also generates a matrix <CODE>y</CODE> of | |
| 53 the outputs of the MLP and a matrix <CODE>z</CODE> of the hidden | |
| 54 unit activations where each row corresponds to one pattern. | |
| 55 | |
| 56 <p><CODE>[mixparams, y, z, a] = mlpfwd(net, x)</CODE> also returns a matrix <CODE>a</CODE> | |
| 57 giving the summed inputs to each output unit, where each row | |
| 58 corresponds to one pattern. | |
| 59 | |
| 60 <p><h2> | |
| 61 See Also | |
| 62 </h2> | |
| 63 <CODE><a href="mdn.htm">mdn</a></CODE>, <CODE><a href="mdn2gmm.htm">mdn2gmm</a></CODE>, <CODE><a href="mdnerr.htm">mdnerr</a></CODE>, <CODE><a href="mdngrad.htm">mdngrad</a></CODE>, <CODE><a href="mlpfwd.htm">mlpfwd</a></CODE><hr> | |
| 64 <b>Pages:</b> | |
| 65 <a href="index.htm">Index</a> | |
| 66 <hr> | |
| 67 <p>Copyright (c) Ian T Nabney (1996-9) | |
| 68 <p>David J Evans (1998) | |
| 69 | |
| 70 </body> | |
| 71 </html> |