Noise Facilitation in Associative Memories of Exponential Capacity

TL;DR

This paper demonstrates that internal noise in associative memory models can enhance recall performance without reducing capacity, challenging the traditional view that noiseless neurons are ideal for memory functions.

Contribution

It provides an analytical framework showing how internal noise can improve associative memory recall and maintains exponential capacity, supported by computational experiments.

Findings

Internal noise can improve recall performance.

Memory capacity remains exponential despite noise.

Computational results support theoretical predictions.

Abstract

Recent advances in associative memory design through structured pattern sets and graph-based inference algorithms have allowed reliable learning and recall of an exponential number of patterns. Although these designs correct external errors in recall, they assume neurons that compute noiselessly, in contrast to the highly variable neurons in brain regions thought to operate associatively such as hippocampus and olfactory cortex. Here we consider associative memories with noisy internal computations and analytically characterize performance. As long as the internal noise level is below a specified threshold, the error probability in the recall phase can be made exceedingly small. More surprisingly, we show that internal noise actually improves the performance of the recall phase while the pattern retrieval capacity remains intact, i.e., the number of stored patterns does not reduce with noise (up to a threshold). Computational experiments lend additional support to our theoretical analysis. This work suggests a functional benefit to noisy neurons in biological neuronal networks.