InitSOM

initializes the weight vectors of a self organizing map (SOM) with a regular grid.

Calling Sequence

[SOMWeights] = InitSOM(Samples, GridSize, GridType)

Parameters

Samples:: matrix that includes sample vectors as rows
GridSize:: vector or scalar, specifies the number of neurons per SOM dimension. All elements must be greater than one.
GridType:: string, can be 'equidistant' or 'adjusted', is not case sensitive
SOMWeight:: matrix that includes weight vectors as rows

Description

This function initializes the weight vectors of a self organizing map with a regular grid. This grid is centered at the mean vector of the samples and aligned according to the principal components. The grid can be equidistant [1] or adjusted to the density of samples in the axis directions [2].

Examples

global CLUSTER_PATH;
Source = read_csv(CLUSTER_PATH + 'demos\IrisData.csv', ascii(9));
Samples = strtod(Source(:, 1 : 4));
SOMWeights = InitSOM(Samples, [5 3], 'equidistant')