# Deep ARTMAP: Generalized Hierarchical Learning with Adaptive Resonance Theory

arXiv: https://arxiv.org/abs/2503.07641 · HTML: https://mlsanity.com/paper/2503.07641/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 18 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 2 of 2)

- [Distributed dual vigilance fuzzy adaptive resonance theory learns online, retrieves arbitrarily-shaped clusters, and mitigates order dependence](https://mlsanity.com/paper/1901.00794/) (2018)
- [A Survey of Adaptive Resonance Theory Neural Network Models for Engineering Applications](https://mlsanity.com/paper/1905.11437/) (2019)

## Built on by (most cited first, 1 of 1)

- [Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics](https://mlsanity.com/paper/2605.06902/) (2026)

## Abstract (arXiv)

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.