Hierarchical Clustering with ART Neural Networks


Author: Guszti Bartfai
Source: GZipped PostScript (51kb); Adobe PDF (234kb)

This paper introduces the concept of a modular neural network structure, which is capable of clustering input patterns through unsupervised learning, and representing a self-consistent hierarchy of clusters at several levels of specificity. In particular, we use the ART neural network as a building block, and name our architecture SMART (for Self-consistent Modular ART). We also show some experimental results for ``proof-of-concept'' using the ARTMAP network, that can be seen as an implementation of a two-level SMART network.

[Up to Computer Science Technical Report Archive: Home Page]