Excitatory/Inhibitory Balance Emerges as a Key Factor for RBN Performance, Overriding Attractor Dynamics

TL;DR

This paper investigates how excitatory and inhibitory balance in Random Boolean Networks influences reservoir computing performance, revealing that specific balance conditions optimize memory and prediction tasks independently of attractor dynamics.

Contribution

It demonstrates that excitatory/inhibitory balance determines critical points for optimal performance in RBNs, providing a systematic approach to reservoir network design.

Findings

Positive excitatory balance enhances memory performance.

Negative inhibitory balance improves prediction performance.

Attractor dynamics have minimal impact on task performance.

Abstract

Reservoir computing provides a time and cost-efficient alternative to traditional learning methods.Critical regimes, known as the "edge of chaos," have been found to optimize computational performance in binary neural networks. However, little attention has been devoted to studying reservoir-to-reservoir variability when investigating the link between connectivity, dynamics, and performance. As physical reservoir computers become more prevalent, developing a systematic approach to network design is crucial. In this article, we examine Random Boolean Networks (RBNs) and demonstrate that specific distribution parameters can lead to diverse dynamics near critical points. We identify distinct dynamical attractors and quantify their statistics, revealing that most reservoirs possess a dominant attractor. We then evaluate performance in two challenging tasks, memorization and prediction, and find that a positive excitatory balance produces a critical point with higher memory performance. In comparison, a negative inhibitory balance delivers another critical point with better prediction performance. Interestingly, we show that the intrinsic attractor dynamics have little influence on performance in either case.