Optimal nonlinear information processing capacity in delay-based reservoir computers

TL;DR

This paper investigates how to optimally configure delay-based reservoir computers by modeling the relationship between their parameters and performance, enabling efficient design without exhaustive parameter searches.

Contribution

It introduces a method to analytically link reservoir parameters to performance, facilitating optimal architecture selection in delay-based reservoir computing systems.

Findings

Identifies optimal reservoir regimes for enhanced performance

Provides a functional model linking parameters to processing capacity

Reduces the need for extensive parameter tuning

Abstract

Reservoir computing is a recently introduced brain-inspired machine learning paradigm capable of excellent performances in the processing of empirical data. We focus in a particular kind of time-delay based reservoir computers that have been physically implemented using optical and electronic systems and have shown unprecedented data processing rates. Reservoir computing is well-known for the ease of the associated training scheme but also for the problematic sensitivity of its performance to architecture parameters. This article addresses the reservoir design problem, which remains the biggest challenge in the applicability of this information processing scheme. More specifically, we use the information available regarding the optimal reservoir working regimes to construct a functional link between the reservoir parameters and its performance. This function is used to explore various properties of the device and to choose the optimal reservoir architecture, thus replacing the tedious and time consuming parameter scannings used so far in the literature.