Supplementary reading: Ultsch and Moerchen’s paper about their Emergent Self-Organizing Maps tool

Ultsch and Moerchen’s report introduces two ideas to model evolving vector fields: to model the tension structure vs. the content structure (i.e. content distribution) of a high-dimensional dataset by its mapping to a 2-dimensional representation.

Ultsch, A., & Moerchen, F. 2005. ESOM-Maps: tools for clustering, visualization, and classification with Emergent SOM. Technical Report Dept. of Mathematics and Computer Science, University of Marburg, Germany, No. 46.


Estimated time required 5-6 hours. Key components to digest are how high-dimensional topological properties are preserved through low-dimensional  mapping, and how a continuous (i.e. field) representation is computed from discrete data by interpolation.