A self-organizing map package with three distinguishing features: (1) Automatic cluster centroid detection and visualization using starbursts. (2) Maintains two models of the data: (a) a self-organizing map model (b) a centroid based clustering model. (3) A very efficient stochastic training algorithm based on ideas from tensor algebra.
R package for self-organizing maps contains state of the art learning algorithms, visualizations, and evaluation functions.