Mutual Information of Three-State Low Activity Diluted Neural Networks with Self-Control

TL;DR

This paper investigates how a self-adaptive threshold improves retrieval performance in three-state diluted neural networks with low activity, focusing on mutual information as a key measure.

Contribution

It introduces a self-control mechanism for the threshold that enhances retrieval quality and capacity in low activity neural networks, validated through numerical analysis.

Findings

Self-control improves storage capacity and basins of attraction.

Mutual information effectively measures retrieval quality.

Numerical results confirm enhanced performance with self-adaptation.

Abstract

The influence of a macroscopic time-dependent threshold on the retrieval process of three-state extremely diluted neural networks is examined. If the threshold is chosen appropriately in function of the noise and the pattern activity of the network, adapting itself in the course of the time evolution, it guarantees an autonomous functioning of the network. It is found that this self-control mechanism considerably improves the retrieval quality, especially in the limit of low activity, including the storage capacity, the basins of attraction and the information content. The mutual information is shown to be the relevant parameter to study the retrieval quality of such low activity models. Numerical results confirm these observations.