Coupled Neural Associative Memories

TL;DR

This paper introduces a new neural associative memory architecture inspired by the visual cortex, capable of learning many patterns and recalling them accurately in noisy conditions, outperforming previous models.

Contribution

It presents a novel coupled neural associative memory design inspired by cortical structures, achieving high noise resilience and large pattern storage simultaneously.

Findings

Significantly improved noise elimination during recall.

Supports exponentially large pattern storage capacity.

Empirical results validate theoretical performance improvements.

Abstract

We propose a novel architecture to design a neural associative memory that is capable of learning a large number of patterns and recalling them later in presence of noise. It is based on dividing the neurons into local clusters and parallel plains, very similar to the architecture of the visual cortex of macaque brain. The common features of our proposed architecture with those of spatially-coupled codes enable us to show that the performance of such networks in eliminating noise is drastically better than the previous approaches while maintaining the ability of learning an exponentially large number of patterns. Previous work either failed in providing good performance during the recall phase or in offering large pattern retrieval (storage) capacities. We also present computational experiments that lend additional support to the theoretical analysis.