Robust Associative Memories Naturally Occuring From Recurrent Hebbian Networks Under Noise

TL;DR

This paper demonstrates that noise and energy constraints in recurrent Hebbian networks can naturally lead to the emergence of robust associative memories, aligning with state-of-the-art binary sparse memory models.

Contribution

It introduces a simplified brain noise model, incorporates energy constraints, and shows how these factors produce robust associative memories in recurrent Hebbian networks.

Findings

Noise can be modeled as insertions and erasures in neural inputs.

Energy constraints and Hebbian learning lead to the formation of associative memories.

The resulting networks match the performance of state-of-the-art binary sparse memories.

Abstract

The brain is a noisy system subject to energy constraints. These facts are rarely taken into account when modelling artificial neural networks. In this paper, we are interested in demonstrating that those factors can actually lead to the appearance of robust associative memories. We first propose a simplified model of noise in the brain, taking into account synaptic noise and interference from neurons external to the network. When coarsely quantized, we show that this noise can be reduced to insertions and erasures. We take a neural network with recurrent modifiable connections, and subject it to noisy external inputs. We introduce an energy usage limitation principle in the network as well as consolidated Hebbian learning, resulting in an incremental processing of inputs. We show that the connections naturally formed correspond to state-of-the-art binary sparse associative memories.