SOM Toolbox Online documentation



 Initializes a SOM linearly along its greatest eigenvectors.



 Initializes a SOM linearly. If necessary, a map struct is created
 first. The initialization is made by first calculating the eigenvalues
 and eigenvectors of the training data. Then, the map is initialized
 along the mdim greatest eigenvectors of the training data, where
 mdim is the dimension of the map grid.


 Kohonen, T., "Self-Organizing Map", 2nd ed., Springer-Verlag, 
    Berlin, 1995, pp. 106-107.

Required input arguments

  D                 The training data.
           (struct) Data struct. If this is given, its '.comp_names' and 
                    '.comp_norm' fields are copied to the map struct.
           (matrix) data matrix, size dlen x dim

Optional input arguments

  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. 

  Here are the valid argument IDs and corresponding values. The values 
  which are unambiguous (marked with '*') can be given without the 
  preceeding argID.
  'dlen'         (scalar) length of the training data
  'data'         (matrix) the training data
                *(struct) the training data
  'munits'       (scalar) number of map units
  'msize'        (vector) map size
  'lattice'     *(string) map lattice: 'hexa' or 'rect'
  'shape'       *(string) map shape: 'sheet', 'cyl' or 'toroid'
  'topol'       *(struct) topology struct
  'som_topol','sTopol'    = 'topol'
  'map'         *(struct) map struct
  'som_map','sMap'        = 'map'

Output arguments

  sMap     (struct) The initialized map struct.


  sMap = som_lininit(D);
  sMap = som_lininit(D,sMap);
  sMap = som_lininit(D,'msize',[10 10]);
  sMap = som_lininit(D,'munits',100,'rect');

See also

som_map_struct Create a map struct.
som_randinit Initialize a map with random values.
som_make Initialize and train self-organizing map.