Reservoir computing with a single time-delay autonomous Boolean node

TL;DR

This paper demonstrates that a single autonomous Boolean logic node with time-delay feedback can be used as a physical reservoir computer to classify short input patterns with high accuracy.

Contribution

It introduces a novel reservoir computing system based on a single Boolean node with delay feedback, showing its effectiveness for short pattern classification.

Findings

Reservoir generates a chaotic transient lasting 30-300 ns.

The system classifies four input patterns for 70 ns.

Performance decreases over time but remains effective for short durations.

Abstract

We demonstrate reservoir computing with a physical system using a single autonomous Boolean logic element with time-delay feedback. The system generates a chaotic transient with a window of consistency lasting between 30 and 300 ns, which we show is sufficient for reservoir computing. We then characterize the dependence of computational performance on system parameters to find the best operating point of the reservoir. When the best parameters are chosen, the reservoir is able to classify short input patterns with performance that decreases over time. In particular, we show that four distinct input patterns can be classified for 70 ns, even though the inputs are only provided to the reservoir for 7.5 ns.