Training Passive Photonic Reservoirs with Integrated Optical Readout

TL;DR

This paper explores training algorithms for passive photonic reservoirs with integrated optical readout, enabling all-optical processing to achieve high-speed, low-energy computing, and compares different methods through numerical simulations.

Contribution

It proposes a novel training algorithm that allows observing complex reservoir states via adjustable readout weights, facilitating fully optical reservoir computing.

Findings

The proposed method effectively observes reservoir states with adjustable weights.

Simulation results show competitive performance compared to ideal and black-box methods.

The approach advances the feasibility of integrated all-optical reservoir computing.

Abstract

As Moore's law comes to an end, neuromorphic approaches to computing are on the rise. One of these, passive photonic reservoir computing, is a strong candidate for computing at high bitrates (> 10 Gbps) and with low energy consumption. Currently though, both benefits are limited by the necessity to perform training and readout operations in the electrical domain. Thus, efforts are currently underway in the photonic community to design an integrated optical readout, which allows to perform all operations in the optical domain. In addition to the technological challenge of designing such a readout, new algorithms have to be designed in order to train it. Foremost, suitable algorithms need to be able to deal with the fact that the actual on-chip reservoir states are not directly observable. In this work, we investigate several options for such a training algorithm and propose a solution in which the complex states of the reservoir can be observed by appropriately setting the readout weights, while iterating over a predefined input sequence. We perform numerical simulations in order to compare our method with an ideal baseline requiring full observability as well as with an established black-box optimization approach (CMA-ES).