This paper presents Deep ARTMAP, a novel extension of the ARTMAP architecture that generalizes the self-consistent modular ART (SMART) architecture to enable hierarchical learning (supervised and unsupervised) across arbitrary transformations of data. The Deep ARTMAP framework operates as a divisive clustering mechanism, supporting an arbitrary number of modules with customizable granularity within each module. Inter-ART modules regulate the clustering at each layer, permitting unsupervised learning while enforcing a one-to-many mapping from clusters in one layer to the next. While Deep ARTMAP reduces to both ARTMAP and SMART in particular configurations, it offers significantly enhanced flexibility, accommodating a broader range of data transformations and learning modalities.
@article{arxiv.2503.07641,
title = {Deep ARTMAP: Generalized Hierarchical Learning with Adaptive Resonance Theory},
author = {Niklas M. Melton and Leonardo Enzo Brito da Silva and Sasha Petrenko and Donald. C. Wunsch},
journal= {arXiv preprint arXiv:2503.07641},
year = {2025}
}