Advances in photonic reservoir computing

TLDR

Reservoir computing is a bio‑inspired, time‑dependent information processing paradigm that offers universal computation through a complex, high‑dimensional transient response without requiring training, making it especially suitable for optics due to its minimal hardware demands. This review aims to introduce and assess a novel analogue neuromorphic optical computing paradigm that implements reservoir computing by encoding information in the intensity and phase of optical fields. The authors examine two principal optical reservoir implementations: networks of multiple discrete optical nodes and a continuous system comprising a single nonlinear device coupled to delayed feedback.

Abstract

Abstract We review a novel paradigm that has emerged in analogue neuromorphic optical computing. The goal is to implement a reservoir computer in optics, where information is encoded in the intensity and phase of the optical field. Reservoir computing is a bio-inspired approach especially suited for processing time-dependent information. The reservoir’s complex and high-dimensional transient response to the input signal is capable of universal computation. The reservoir does not need to be trained, which makes it very well suited for optics. As such, much of the promise of photonic reservoirs lies in their minimal hardware requirements, a tremendous advantage over other hardware-intensive neural network models. We review the two main approaches to optical reservoir computing: networks implemented with multiple discrete optical nodes and the continuous system of a single nonlinear device coupled to delayed feedback.