Machine learning with photonic delay systems

Machine learning can figure out how to perform important tasks by generalizing from data. Nowadays, machine learning is all around us: forecast weather prediction, customized product recommendations, or automatic face recognition are examples of machine learning. The field underwent a burst of activity, thanks to the availability of large amount of data and the increment of computational power. In this work, I will give a brief introduction on machine learning to finally focus in two techniques of the field, reservoir computing and extreme learning machines. In our recent work, we present a unified framework for extreme learning machines and reservoir computing (echo state networks), which can be physically and efficiently implemented using a delay system.