Information Spaces using a Self-Organizing Map

Daniel X. Pape
Community Architectures for Network Information Systems
University of Illinois at Urbana-Champaign
Champaign, IL 61820 USA
dpape@canis.uiuc.edu

The Unified Matrix method [1], was developed by Alfred Ultsch to help
determine natural clusters found by a self-organizing map [2]. The
Interspace project at UIUC's CANIS laboratory uses data obtained by
noun-phrase parsing of document sets, and Ultsch's U-Matrix method to
visualize these so-called Information Spaces. Users of this
visualization are able to navigate the space and browse the
self-organized document collection.


Keywords: Visualization, Information Space, Self-Organizing Map, Unified
Matrix


References:

1. Ultsch, A.: Self-organizing Neural Networks for Visualization and
Classification, in O.Opitz, B. Lausen and R. Klar, (Eds.)  Information
and Classification, 1993. Berlin: Springer-Verlag, pp 307-313.

2. Kohonen, T. Self-Organizing Maps. Springer, Berlin,
Heidelberg. (Second Extended Edition, 1997)