Modular DFR: Digital Delayed Feedback Reservoir Model for Enhancing Design Flexibility

TL;DR

This paper introduces a modular digital delayed feedback reservoir model that enhances design flexibility, reduces power consumption, and improves throughput in hardware implementations of reservoir computing systems.

Contribution

A novel modular digital DFR model that simplifies hyperparameter tuning, allows flexible nonlinear function selection, and demonstrates significant power and throughput improvements.

Findings

Achieved 10x power reduction compared to traditional analog DFRs.

Realized 5.3x throughput improvement with maintained accuracy.

Flexible nonlinear functions enhance digital DFR performance.

Abstract

A delayed feedback reservoir (DFR) is a type of reservoir computing system well-suited for hardware implementations owing to its simple structure. Most existing DFR implementations use analog circuits that require both digital-to-analog and analog-to-digital converters for interfacing. However, digital DFRs emulate analog nonlinear components in the digital domain, resulting in a lack of design flexibility and higher power consumption. In this paper, we propose a novel modular DFR model that is suitable for fully digital implementations. The proposed model reduces the number of hyperparameters and allows flexibility in the selection of the nonlinear function, which improves the accuracy while reducing the power consumption. We further present two DFR realizations with different nonlinear functions, achieving 10x power reduction and 5.3x throughput improvement while maintaining equal or better accuracy.