Synopsis

A Clusterer that implements Kohonen's Self Organizing Map algorithm for unsupervised clustering.

This clusterer is available in the SelfOrganizingMap package.

Options

The table below describes the options available for SelfOrganizingMap.

Option	Description
calcStats	This should calculate statistics for each cluster after training.
convergenceEpochs	The number of epochs in convergence phase.
debug	If set to true, clusterer may output additional info to the console.
doNotCheckCapabilities	If set, clusterer capabilities are not checked before clusterer is built (Use with caution to reduce runtime).
height	The height of lattice.
learningRate	The initial amount the weights are updated.
normalizeAttributes	This will normalize the attributes.
orderingEpochs	The number of epochs in ordering phase.
width	The width of lattice.

The table below describes the capabilities of SelfOrganizingMap.

Capability	Supported
Class	No class
Attributes	Binary attributes, Unary attributes, Nominal attributes, Empty nominal attributes, Missing values, Numeric attributes
Min # of instances	1