A Biologically Plausible Dense Associative Memory with Exponential Capacity

TL;DR

This paper introduces a biologically plausible associative memory model with exponential capacity by using a novel threshold nonlinearity, enabling distributed representations and high storage capacity beyond previous limitations.

Contribution

The authors propose a new associative memory network with threshold nonlinearity that allows distributed representations, significantly increasing capacity to exponential in hidden units, overcoming prior winner-take-all constraints.

Findings

Achieves exponential capacity in hidden units

Supports distributed, compositional memory representations

Maintains class-discriminative structure in low-dimensional hidden space

Abstract

Krotov and Hopfield (2021) proposed a biologically plausible two-layer associative memory network with memory storage capacity exponential in the number of visible neurons. However, the capacity was only linear in the number of hidden neurons. This limitation arose from the choice of nonlinearity between the visible and hidden units, which enforced winner-take-all dynamics in the hidden layer, thereby restricting each hidden unit to encode only a single memory. We overcome this limitation by introducing a novel associative memory network with a threshold nonlinearity that enables distributed representations. In contrast to winner-take-all dynamics, where each hidden neuron is tied to an entire memory, our network allows hidden neurons to encode basic components shared across many memories. Consequently, complex patterns are represented through combinations of hidden neurons. These representations reduce redundancy and allow many correlated memories to be stored compositionally. Thus, we achieve much higher capacity: exponential in the number of hidden units, provided the number of visible units is sufficiently large relative to the number of hidden units. Exponential capacity arises because all binary states of the hidden units can become stable memory patterns. Moreover, the distributed hidden representation, which has much lower dimensionality than the visible layer, preserves class-discriminative structure, supporting efficient nonlinear decoding. These results establish a new regime for associative memory, enabling high-capacity, robust, and scalable architectures consistent with biological constraints.