Response Functions Improving Performance in Analog Attractor Neural Networks

TL;DR

This paper investigates how response functions can enhance the performance of analog attractor neural networks by stabilizing memory retrieval states and reducing interference, with implications for storage capacity.

Contribution

It introduces a simple dynamics that stabilizes highly correlated states, improving memory retrieval in analog neural networks within a certain capacity limit.

Findings

Stabilization of network states correlated with retrieved patterns.

Enhanced storage capacity up to a certain load factor.

Dependence of capacity on global activity level.

Abstract

In the context of attractor neural networks, we study how the equilibrium analog neural activities, reached by the network dynamics during memory retrieval, may improve storage performance by reducing the interferences between the recalled pattern and the other stored ones. We determine a simple dynamics that stabilizes network states which are highly correlated with the retrieved pattern, for a number of stored memories that does not exceed $\alpha_{\star} N$, where $\alpha_{\star}\in[0,0.41]$ depends on the global activity level in the network and $N$ is the number of neurons.