Excitatory/inhibitory balance emerges as a key factor for RBN performance, overriding attractor dynamics

Frontiers in Computational Neuroscience

Neuroscience

Bertrand Reulet¹  Emmanuel Calvet²  Jean Rouat² 

[1]Département de Physique, Faculté des Sciences, Institut Quantique, Université de Sherbrooke, Sherbrooke, QC, Canada

[2]Neurosciences Computationelles et Traitement Intelligent des Signaux (NECOTIS), Faculté de Génie, Génie Électrique et Génie Informatique (GEGI), Université de Sherbrooke, Sherbrooke, QC, Canada

关键词: reservoir computing;    RBN;    criticality;    attractor;    memory;    prediction;   

DOI  :  10.3389/fncom.2023.1223258

 received in 2023-05-15, accepted in 2023-07-17,  发布年份 2023

来源: Frontiers

【 摘 要 】

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.

【 授权许可】

Unknown   
Copyright © 2023 Calvet, Rouat and Reulet.