Nonlinear photonic dynamical systems for unconventional computing

TL;DR

This paper reviews recent advances in nonlinear photonic dynamical systems, especially photonic reservoir computing, highlighting progress, challenges, and future directions for hardware-efficient and autonomous photonic neural networks.

Contribution

It provides a comprehensive overview of photonic reservoir computing and discusses future challenges in implementing deep neural networks and autonomous photonic systems.

Findings

Photonic reservoir computing can be implemented via spatio-temporal or delay systems.

Recent progress includes hardware-friendly learning methods and autonomous photonic neural networks.

Future challenges involve integrating deep neural networks and reducing digital hardware dependence.

Abstract

Driven by the remarkable breakthroughs during the past decade, photonics neural networks have experienced a revival. Here, we provide a general overview of progress over the past decade, and sketch a roadmap of important future developments. We focus on photonic implementations of the reservoir computing machine learning paradigm, which offers a conceptually simple approach that is amenable to hardware implementations. In particular, we provide an overview of photonic reservoir computing implemented via either spatio temporal or delay dynamical systems. Going beyond reservoir computing, we discuss recent advances and future challenges of photonic implementations of deep neural networks, of the quest for learning methods that are hardware-friendly as well as realizing autonomous photonic neural networks, i.e. with minimal digital electronic auxiliary hardware.