Photonic reservoir computing for energy efficient and versatile machine learning application

Abstract

Time-multiplexed reservoir computing is a machine learning concept which can be realised in photonic hardware systems using only one physical node. The concept can be used for various problems, ranging from classification problems to time-series prediction tasks, while being fast and energy efficient. Here, a theoretical analysis of a reservoir computer realised via delay-coupled semiconductor lasers is presented and the role of the internal system time-scales and the bifurcation structure is discussed. It is further shown that optimal performance can be reached by tailoring the coupling delays to the specific memory requirements of the given task.