Short-term synaptic facilitation improves information retrieval in noisy neural networks

TL;DR

This paper investigates how short-term synaptic facilitation enhances the ability of autoassociative neural networks to retrieve information accurately in noisy environments, extending previous studies to more realistic conditions.

Contribution

It provides a comprehensive analysis of synaptic facilitation effects on neural network performance under noise, including phase diagrams and critical temperature evaluations.

Findings

Facilitation enlarges the good retrieval region.

Networks with facilitation tolerate higher noise levels.

Facilitation increases critical temperature thresholds.

Abstract

Short-term synaptic depression and facilitation have been found to greatly influence the performance of autoassociative neural networks. However, only partial results, focused for instance on the computation of the maximum storage capacity at zero temperature, have been obtained to date. In this work, we extended the study of the effect of these synaptic mechanisms on autoassociative neural networks to more realistic and general conditions, including the presence of noise in the system. In particular, we characterized the behavior of the system by means of its phase diagrams, and we concluded that synaptic facilitation significantly enlarges the region of good retrieval performance of the network. We also found that networks with facilitating synapses may have critical temperatures substantially higher than those of standard autoassociative networks, thus allowing neural networks to perform better under high-noise conditions.