Deep ARTMAP: Generalized Hierarchical Learning with Adaptive Resonance Theory
This work addresses the need for more adaptable hierarchical learning systems in machine learning, though it appears incremental as it builds directly on ARTMAP and SMART architectures.
The paper tackles the problem of enabling hierarchical learning across arbitrary data transformations by extending the ARTMAP architecture, resulting in Deep ARTMAP which offers significantly enhanced flexibility compared to existing methods.
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.