The Category Map service classifies an information corpus into different conceptual categories using a variant of Kohonen's self-organizing feature map (SOM). The SOM is a neural network which serves as vector quantizer to map high-dimensional feature vectors onto a two dimensional grid. A multi-layer Category Map is used to form a hierarchical set of categorizations for large corpora.

Several techniques have been incorporated in this service to assist the user in visualizing the hierarchical categorization. The service transforms two dimensional output maps into three dimensional terrains which users can navigate via information spaceflight to investigate clusters of semantic locality.