Photonic Reservoir Computing

Reservoir computing is a brain inspired artificial intelligence algorithm with excellent performance on tasks such as speech recognition and time series prediction. The reservoir computing algorithm can be easily implemented in hardware. We present photonic implementations based on a simple architecture consisting of a single nonlinear node and a delay line. We also present an implementation in which the internal variables (the neurons) are represented by the amplitudes of a frequency comb. We discuss the advantages and disadvantages of these implementations, how to create an optical output, how to mitigate the effect of noise, how to realize advanced information processing for instance by coupling the output of the reservoir back into itself. We discuss the future of photonic reservoir computing and more generally of analog brain inspired computing.