Computational Capabilities of Random Automata Networks for Reservoir Computing

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.

9 pages, 6 figures

References in corpus (3)

• Revisiting the Edge of Chaos: Evolving Cellular Automata to Perform Computations
• Damage Spreading and Criticality in Finite Random Dynamical Networks
• Emergent Criticality Through Adaptive Information Processing in Boolean Networks

Cited by in corpus (14)

• Recent Advances in Physical Reservoir Computing: A Review
• Reservoir computing with a single time-delay autonomous Boolean node
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Cellular automata inspired multistable origami metamaterials for mechanical learning
• Feedback-driven quantum reservoir computing for time-series analysis
• Symmetry-Aware Reservoir Computing
• Passive frustrated nanomagnet reservoir computing
• Coevolution of Information Processing and Topology in Hierarchical Adaptive Random Boolean Networks
• Product Reservoir Computing: Time-Series Computation with Multiplicative Neurons
• Spoken Digit Classification by In-Materio Reservoir Computing with Neuromorphic Atomic Switch Networks
• DNA Reservoir Computing: A Novel Molecular Computing Approach
• Excitatory/Inhibitory Balance Emerges as a Key Factor for RBN Performance, Overriding Attractor Dynamics
• Exploring Transfer Function Nonlinearity in Echo State Networks
• Adaptive model selection in photonic reservoir computing by reinforcement learning