Adaptive resonance associative map: a hierarchical ART system for fast stable associative learning

摘要

The author introduces a new class of predictive ART architectures, called the adaptive resonance associative map (ARAM), which performs rapid, yet stable heteroassociative learning in a real-time environment. ARAM can be visualized as two ART modules sharing a single recognition code layer. The unit for recruiting a recognition code is a pattern pair. Code stabilization is ensured by restricting coding to states where resonances are reached in both modules. Simulation results have shown that ARAM is capable of self-stabilizing association of arbitrary pattern pairs of arbitrary complexity appearing in arbitrary sequence by fast learning in a real-time environment. Due to the symmetrical network structure, associative recall can be performed in both directions.