Adaptive Hierarchical Incremental Grid Growing: An architecture for high-dimensional data visualization
Dieter Merkl, Shao Hui He, Michael Dittenbach, Andreas Rauber · 2003
Abstract — Based on the principles of the self-organizing map, we have designed a novel neural net-work model with a highly adaptive hierarchically struc-tured architecture, the adaptive hierarchical incremen-tal grid growing. This feature allows it to capture the unknown data topology in terms of hierarchical rela-tionships and cluster structures in a highly accurate way. In particular, unevenly distributed real-world data is represented in a suitable network structure ac-cording to its specific requirements during the unsuper-vised training process. The resulting three-dimensional arrangement of mutually independent maps reveals a precise view of the inherent topology of the data set. 1