ESOM: an algorithm to evolve self-organizing maps from online data streams
Jeremiah D. Deng, Nikola Kirilov Kasabov · 2000
An algorithm of evolving self-organizing map (ESOM) is proposed as a dynamic version of the Kohonen self-organizing map, where network structure is evolved in an online adaptive mode. Experiments have been carried out on some benchmark data sets as well as on macroeconomic data. Results show that ESOM is a good tool for clustering, data analysis, and visualisation.