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

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.

arXiv comment22 pages, 6 figures

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Recent Advances in Physical Reservoir Computing: A Review
• Optimal Dynamical Range of Excitable Networks at Criticality
• Dynamical phase transitions in quantum reservoir computing
• Investigating echo state networks dynamics by means of recurrence analysis
• Rapid Time Series Prediction with a Hardware-Based Reservoir Computer
• Computational Capabilities of Random Automata Networks for Reservoir Computing
• Edge of chaos and avalanches in neural networks with heavy-tailed synaptic weight distribution
• The topology of the directed clique complex as a network invariant
• Avalanches and Generalized Memory Associativity in a Network Model for Conscious and Unconscious Mental Functioning
• P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware