Reservoir computing based on laser subject to optoelectronic feedback

We study delay-based photonic reservoir computing using a semiconductor laser with an optoelectronic feedback. We investigate the connection between the bifurcation landscape of this system with the computational performance of the reservoir. Specifically, there are multiple Hopf bifurcation branches possessing the parity asymmetry with relation to the feedback sign. We observe the corresponding difference in the normalized means square error (NMSE) values using the prediction on the chaotic Santa-Fe time series as a benchmark.