An introduction to reservoir computing

TL;DR

This paper introduces reservoir computing, a neural network paradigm that uses physical systems with high-dimensional recurrent networks, highlighting its concepts, implementations across various physical domains, and potential quantum extensions.

Contribution

It provides a comprehensive overview of reservoir computing, including its fundamental principles, diverse physical implementations, and emerging quantum approaches.

Findings

Reservoir computing enables training of physical neural networks by only adjusting the output layer.

Physical implementations span electronics, photonics, spintronics, mechanics, and biology.

Quantum reservoir computing is a promising emerging field.

Abstract

There is a growing interest in the development of artificial neural networks that are implemented in a physical system. A major challenge in this context is that these networks are difficult to train since training here would require a change of physical parameters rather than simply of coefficients in a computer program. For this reason, reservoir computing, where one employs high-dimensional recurrent networks and trains only the final layer, is widely used in this context. In this chapter, I introduce the basic concepts of reservoir computing. Moreover, I present some important physical implementations coming from electronics, photonics, spintronics, mechanics, and biology. Finally, I provide a brief discussion of quantum reservoir computing.