Semantically-correlated memories in a dense associative model
This work addresses memory modeling for AI and neuroscience, offering a unified framework with incremental improvements over existing dense associative models.
The authors tackled the problem of associative memory for continuous-valued patterns by introducing the Correlated Dense Associative Memory (CDAM), which integrates auto- and hetero-association using a graph structure and anti-Hebbian learning, resulting in four dynamical modes and applications in neuroscience experiments, image retrieval, and automata simulation.
I introduce a novel associative memory model named Correlated Dense Associative Memory (CDAM), which integrates both auto- and hetero-association in a unified framework for continuous-valued memory patterns. Employing an arbitrary graph structure to semantically link memory patterns, CDAM is theoretically and numerically analysed, revealing four distinct dynamical modes: auto-association, narrow hetero-association, wide hetero-association, and neutral quiescence. Drawing inspiration from inhibitory modulation studies, I employ anti-Hebbian learning rules to control the range of hetero-association, extract multi-scale representations of community structures in graphs, and stabilise the recall of temporal sequences. Experimental demonstrations showcase CDAM's efficacy in handling real-world data, replicating a classical neuroscience experiment, performing image retrieval, and simulating arbitrary finite automata.