Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold

TL;DR

The paper introduces MESH, a novel content-addressable memory architecture inspired by brain circuits, that avoids catastrophic forgetting and maintains high recall quality across a wide range of stored patterns.

Contribution

MESH factorizes internal dynamics and external association, enabling a CAM system without the memory cliff, outperforming existing models in information capacity.

Findings

MESH nearly saturates the information bound for CAM networks.

It maintains partial recall with increasing patterns, avoiding catastrophic loss.

Experimental results confirm theoretical advantages.

Abstract

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.