Saved in:
Bibliographic Details
Main Authors: Melton, Niklas M., da Silva, Leonardo Enzo Brito, Petrenko, Sasha, Wunsch II, Donald. C.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.07641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912268555386880
author Melton, Niklas M.
da Silva, Leonardo Enzo Brito
Petrenko, Sasha
Wunsch II, Donald. C.
author_facet Melton, Niklas M.
da Silva, Leonardo Enzo Brito
Petrenko, Sasha
Wunsch II, Donald. C.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07641
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep ARTMAP: Generalized Hierarchical Learning with Adaptive Resonance Theory
Melton, Niklas M.
da Silva, Leonardo Enzo Brito
Petrenko, Sasha
Wunsch II, Donald. C.
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
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.
title Deep ARTMAP: Generalized Hierarchical Learning with Adaptive Resonance Theory
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2503.07641