Self-control dynamics for sparsely coded networks with synaptic noise

TL;DR

This paper introduces a self-control mechanism with a dynamic threshold in sparsely coded neural networks, enhancing retrieval performance and capacity by adapting to noise and pattern activity.

Contribution

It proposes a novel self-regulating threshold that automatically adjusts during network evolution, improving retrieval quality and capacity in noisy, sparsely coded networks.

Findings

Enhanced storage capacity and basins of attraction.

Improved mutual information content.

Automatic adaptation of thresholds improves retrieval dynamics.

Abstract

For the retrieval dynamics of sparsely coded attractor associative memory models with synaptic noise the inclusion of a macroscopic time-dependent threshold is studied. It is shown that if the threshold is chosen appropriately as a function of the cross-talk noise and of the activity of the memorized patterns, adapting itself automatically in the course of the time evolution, an autonomous functioning of the model is guaranteed. This self-control mechanism considerably improves the quality of the fixed-point retrieval dynamics, in particular the storage capacity, the basins of attraction and the mutual information content.