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

arXiv: https://arxiv.org/abs/2308.10831 · HTML: https://mlsanity.com/paper/2308.10831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 60 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Rapid Time Series Prediction with a Hardware-Based Reservoir Computer](https://mlsanity.com/paper/1807.07627/) (2018)
- [Analysis of structure and dynamics in three-neuron motifs](https://mlsanity.com/paper/1811.05225/) (2018)
- [Investigating echo state networks dynamics by means of recurrence analysis](https://mlsanity.com/paper/1601.07381/) (2016)
- [P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware](https://mlsanity.com/paper/2009.05593/) (2020)
- [The topology of the directed clique complex as a network invariant](https://mlsanity.com/paper/1510.00660/) (2015)
- [Memory and Information Processing in Recurrent Neural Networks](https://mlsanity.com/paper/1604.06929/) (2016)
- [Avalanches and Generalized Memory Associativity in a Network Model for Conscious and Unconscious Mental Functioning](https://mlsanity.com/paper/1704.02741/) (2017)

## Abstract (arXiv)

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.