Online training for high-performance analogue readout layers in photonic reservoir computers

TL;DR

This paper demonstrates that online training enables high-performance analogue readout layers in photonic reservoir computers, overcoming previous limitations and matching digital layer performance in processing time-dependent signals.

Contribution

It introduces an online training method for analogue readout layers in reservoir computing, maintaining high performance without added complexity.

Findings

Online learning achieves digital-level performance with analogue layers.

The method simplifies the setup of analogue reservoir computers.

Numerical simulations confirm feasibility and effectiveness.

Abstract

Introduction. Reservoir Computing is a bio-inspired computing paradigm for processing time-dependent signals. The performance of its hardware implementation is comparable to state-of-the-art digital algorithms on a series of benchmark tasks. The major bottleneck of these implementation is the readout layer, based on slow offline post-processing. Few analogue solutions have been proposed, but all suffered from notice able decrease in performance due to added complexity of the setup. Methods. Here we propose the use of online training to solve these issues. We study the applicability of this method using numerical simulations of an experimentally feasible reservoir computer with an analogue readout layer. We also consider a nonlinear output layer, which would be very difficult to train with traditional methods. Results. We show numerically that online learning allows to circumvent the added complexity of the analogue layer and obtain the same level of performance as with a digital layer. Conclusion. This work paves the way to high-performance fully-analogue reservoir computers through the use of online training of the output layers.