2022/02/01 by Sugandha Sharma, Sarthak Chandra, Sharma, Sugandha +3 · 1 citation
Engineering · Mathematics · Neuroscience · #Advanced Memory and Neural Computing #Algorithm #Artificial Intelligence (cs.AI) #Artificial intelligence #Artificial neural network #Auxiliary memory #Combinatorics #Computer hardware #Computer science #Content-addressable memory #Entorhinal cortex #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Forgetting #Hippocampal formation #Information Theory (cs.IT) #Machine Learning (cs.LG) #Mathematics #Memory map #Neural dynamics and brain function #Neuroscience #Parallel computing #Pattern recognition (psychology) #Recall #Set (abstract data type) #Shared memory #Theoretical computer science #Topology (electrical circuits)
paper · pdf · doi:10.48550/arxiv.2202.00159
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2022/02/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Content-addressable memory (CAM) networks, so-called because stored items can be recalled by partial or corrupted versions of the items, exhibit near-perfect recall of a small number of information-dense patterns below capacity and a 'memory cliff' beyond, such that inserting a single additional pattern results in catastrophic loss of all stored patterns. We propose a novel CAM architecture, Memory Scaffold with Heteroassociation (MESH), that factorizes the problems of internal attractor dynamics and association with external content to generate a CAM continuum without a memory cliff: Small numbers of patterns are stored with complete information recovery matching standard CAMs, while inserting more patterns still results in partial recall of every pattern, with a graceful trade-off between pattern number and pattern richness. Motivated by the architecture of the Entorhinal-Hippocampal memory circuit in the brain, MESH is a tripartite architecture with pairwise interactions that uses a predetermined set of internally stabilized states together with heteroassociation between the internal states and arbitrary external patterns. We show analytically and experimentally that for any number of stored patterns, MESH nearly saturates the total information bound (given by the number of synapses) for CAM networks, outperforming all existing CAM models.