Department of Software Technology
Vienna University of Technology
The Growing Hierarchical Self-Organizing Map
In spite of the stability and popularity of the Self-Organizing Map (SOM), at least two limitations have to be noted, which are related, on the one hand, to the static architecture of this model, as well as, on the other hand, to the limited capabilities for the representation of hierarchical relations of the data.
With our novel Growing Hierarchical Self-Organizing Map (GHSOM) we address both limitations.
The growing hierarchical som is an artificial neural network model with
hierarchical architecture composed of independent growing self-organizing
By providing a global orientation of the independently growing
maps in the individual layers of the hierarchy, navigation across branches
The GHSOM is used as a basis for data organization in both the SOMLib and SOMeJB systems, and forms a core component in the KONTERM project.
A short description of the GHSOM neural network architecture and training process.
Some experiments are available for you to explore the characteristics of the GHSOM system.
We provide examples both for large text-collections as well as collections of music files.
A list of some selected publications describing the GHSOM and its applications
The software for the GHSOM system is available for you to
download, both as Matlab and C implementations.
Members of the GHSOM project team
If you have questions or want to provide feedback on any aspect
of the GHSOM, please send an e-mail to