📄 som_sompaktrain.html

📁 Kohonen的SOM软件包
💻 HTML
字号:
<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML//EN"><html><head><title>SOM Toolbox / som_sompaktrain </title></head><body bgcolor=#f0f0f0><table border=0 width="100%" cellpadding=0 cellspacing=0><tr><td valign=baseline><font size=+2>SOM Toolbox</font></td><td valign=baseline align=center><a href="somtoolbox.html">Online documentation</td><td valign=baseline align=right><a href="http://www.cis.hut.fi/projects/somtoolbox/" target="_top">http://www.cis.hut.fi/projects/somtoolbox/</a></td></tr></table><hr><H1> som_sompaktrain </H1><H3> Purpose </H3><PRE> Use SOM_PAK to train the Self-Organizing Map.</PRE><H3> Syntax </H3><UL><PRE>  sM = som_sompaktrain(sM,D);  sM = som_sompaktrain(sM,sD);  sM = som_sompaktrain(...,'argID',value,...);  sM = som_sompaktrain(...,value,...);  [sM,sT] = som_sompaktrain(M,D,...);</PRE></UL><H3> Description </H3><PRE> Trains the given SOM (sM or M above) with the given training data (sD or D) using SOM_PAK. If no optional arguments (argID, value) are given, a default training is done, the parameters are obtained from SOM_TRAIN_STRUCT function.  Using optional arguments the training parameters can be specified. Returns the trained and updated SOM and a train struct which contains information on the training. Notice that the SOM_PAK program 'vsom' must be in the search path of your shell. Alternatively, you can set a variable 'SOM_PAKDIR' in the Matlab workspace to tell the som_sompaktrain where to find the 'vsom' program. Notice also that many of the training parameters are much more limited in values than when using SOM Toolbox function for training:   - the map shape is always 'sheet'   - only initial value for neighborhood radius can be given   - neighborhood function can only be 'bubble' or 'gaussian'   - only initial value for learning rate can be given   - learning rate can only be 'linear' or 'inv'   - mask cannot be used: all variables are always used in BMU search Any parameters not confirming to these restrictions will be converted so that they do before training. On the other hand, there are some  additional options that are not present in the SOM Toolbox:    - random seed   - snapshot file and interval</PRE><H3> Required input arguments </H3><PRE>  sM          The map to be trained.      (struct) map struct     (matrix) codebook matrix (field .data of map struct)              Size is either [munits dim], in which case the map grid               dimensions (msize) should be specified with optional arguments,              or [msize(1) ... msize(k) dim] in which case the map               grid dimensions are taken from the size of the matrix.               Lattice, by default, is 'rect' and shape 'sheet'.  D           Training data.     (struct) data struct     (matrix) data matrix, size [dlen dim]     (string) name of data file</PRE><H3> Optional input arguments </H3><PRE>  argID (string) Argument identifier string (see below).  value (varies) Value for the argument (see below).  The optional arguments can be given as 'argID',value -pairs. If an  argument is given value multiple times, the last one is  used. The valid IDs and corresponding values are listed below. The values   which are unambiguous (marked with '*') can be given without the   preceeding argID.   'msize'        (vector) map grid dimensions. Default is the one                           in sM (field sM.topol.msize) or                            'si = size(sM); msize = si(1:end-1);'                            if only a codebook matrix was given.    'radius_ini'   (scalar) initial neighborhood radius    'radius'       (scalar) = 'radius_ini'   'alpha_ini'    (vector) initial learning rate   'alpha'        (scalar) = 'alpha_ini'   'trainlen'     (scalar) training length (see also 'tlen_type')   'seed'         (scalar) seed for random number generator   'snapfile'     (string) base name for snapshot files   'snapinterval' (scalar) snapshot interval   'tlen_type'   *(string) is the trainlen argument given in 'epochs' or                           in 'samples'. Default is 'epochs'.   'train'       *(struct) train struct, parameters for training.                            Default parameters, unless specified,                            are acquired using SOM_TRAIN_STRUCT (this                            also applies for 'trainlen', 'alpha_type',                           'alpha_ini', 'radius_ini' and 'radius_fin').   'sTrain', 'som_topol' (struct) = 'train'   'neigh'       *(string) The used neighborhood function. Default is                            the one in sM (field '.neigh') or 'gaussian'                           if only a codebook matrix was given. The other                            possible value is 'bubble'.   'topol'       *(struct) topology of the map. Default is the one                           in sM (field '.topol').   'sTopol', 'som_topol' (struct) = 'topol'   'alpha_type'  *(string) learning rate function, 'inv' or 'linear'   'lattice'     *(string) map lattice. Default is the one in sM                           (field sM.topol.lattice) or 'rect'                            if only a codebook matrix was given. </PRE><H3> Output arguments </H3><PRE>  sM          the trained map     (struct) if a map struct was given as input argument, a               map struct is also returned. The current training               is added to the training history (sM.trainhist).              The 'neigh' and 'mask' fields of the map struct              are updated to match those of the training.     (matrix) if a matrix was given as input argument, a matrix              is also returned with the same size as the input               argument.  sT (struct) train struct; information of the accomplished training</PRE><H3> Examples </H3><PRE> Simplest case:  sM = som_sompaktrain(sM,D);    sM = som_sompaktrain(sM,sD);   The change training parameters, the optional arguments 'train',  'neigh','mask','trainlen','radius','radius_ini', 'alpha',  'alpha_type' and 'alpha_ini' are used.   sM = som_sompaktrain(sM,D,'bubble','trainlen',10,'radius_ini',3); Another way to specify training parameters is to create a train struct:  sTrain = som_train_struct(sM,'dlen',size(D,1),'algorithm','seq');  sTrain = som_set(sTrain,'neigh','gaussian');  sM = som_sompaktrain(sM,D,sTrain); You don't necessarily have to use the map struct, but you can operate directly with codebook matrices. However, in this case you have to specify the topology of the map in the optional arguments. The following commads are identical (M is originally a 200 x dim sized matrix):  M = som_sompaktrain(M,D,'msize',[20 10],'lattice','hexa');  M = som_sompaktrain(M,D,'msize',[20 10],'hexa');  sT= som_set('som_topol','msize',[20 10],'lattice','hexa');  M = som_sompaktrain(M,D,sT);  M = reshape(M,[20 10 dim]);  M = som_sompaktrain(M,D,'hexa'); The som_sompaktrain also returns a train struct with information on the  accomplished training. This is the same one as is added to the end of the  trainhist field of map struct, in case a map struct is given.  [M,sTrain] = som_sompaktrain(M,D,'msize',[20 10]);  [sM,sTrain] = som_sompaktrain(sM,D); % sM.trainhist(end)==sTrain</PRE><H3> See also </H3><TABLE NOBORDER WIDTH=80%><TR><TD><a href="som_make.html"><B>som_make</B></a><TD> Initialize and train a SOM using default parameters.<TR><TD><a href="som_seqtrain.html"><B>som_seqtrain</B></a><TD> Train SOM with sequential algorithm.<TR><TD><a href="som_batchtrain.html"><B>som_batchtrain</B></a><TD> Train SOM with batch algorithm.<TR><TD><a href="som_train_struct.html"><B>som_train_struct</B></a><TD> Determine default training parameters.</TABLE><p><hr><br><br><!-- Last updated: May 30 2002 --></body></html>
⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -