Computational Capabilities of Random Automata Networks for Reservoir Computing

TL;DR

This study investigates how Random Boolean Networks can serve as reservoirs in reservoir computing, highlighting the importance of critical connectivity for optimal computational performance in complex heterogeneous systems.

Contribution

It introduces the use of heterogeneous Random Boolean Networks as reservoirs in RC and analyzes their dynamics at critical connectivity for enhanced computational capability.

Findings

Optimal classification performance occurs at critical connectivity.

Balance between separability and fading memory is key.

Heterogeneous RBNs can effectively function as reservoirs.

Abstract

This paper underscores the conjecture that intrinsic computation is maximal in systems at the "edge of chaos." We study the relationship between dynamics and computational capability in Random Boolean Networks (RBN) for Reservoir Computing (RC). RC is a computational paradigm in which a trained readout layer interprets the dynamics of an excitable component (called the reservoir) that is perturbed by external input. The reservoir is often implemented as a homogeneous recurrent neural network, but there has been little investigation into the properties of reservoirs that are discrete and heterogeneous. Random Boolean networks are generic and heterogeneous dynamical systems and here we use them as the reservoir. An RBN is typically a closed system; to use it as a reservoir we extend it with an input layer. As a consequence of perturbation, the RBN does not necessarily fall into an attractor. Computational capability in RC arises from a trade-off between separability and fading memory of inputs. We find the balance of these properties predictive of classification power and optimal at critical connectivity. These results are relevant to the construction of devices which exploit the intrinsic dynamics of complex heterogeneous systems, such as biomolecular substrates.