Reservoir Computing with Superconducting Electronics
This work addresses high-rate signal processing applications by proposing a superconducting reservoir computing platform, but it is incremental as it builds on existing reservoir computing and superconducting logic schemes.
The paper tackled the problem of performing machine learning tasks using physical reservoir computing by leveraging the speed and low power consumption of superconducting electronics, achieving higher-order parity calculations and channel equalization at rates approaching 100 Gb/s in simulations.
The rapidity and low power consumption of superconducting electronics makes them an ideal substrate for physical reservoir computing, which commandeers the computational power inherent to the evolution of a dynamical system for the purposes of performing machine learning tasks. We focus on a subset of superconducting circuits that exhibit soliton-like dynamics in simple transmission line geometries. With numerical simulations we demonstrate the effectiveness of these circuits in performing higher-order parity calculations and channel equalization at rates approaching 100 Gb/s. The availability of a proven superconducting logic scheme considerably simplifies the path to a fully integrated reservoir computing platform and makes superconducting reservoirs an enticing substrate for high rate signal processing applications.