Design of parallel reservoir computing by mutually-coupled semiconductor lasers with optoelectronic feedback

Via implementing parallel tasks including Santa-Fe time series prediction and nonlinear channel equalization, we studied the characteristics of reservoir computing (RC) using two mutually-coupled semiconductor lasers (MC-SLs) with optoelectronic feedback. The influence of system parameters (injection current, coupling strength, scaling factor and coupling time-delays) on RC performance have been investigated in detail. Results show that, the optimized performance is always achieved around the edge of bifurcation points; positive feedback is more preferred when the scaling factor exceeds a certain level; under optimized parameters, both of lower normalized mean squared error (NMSE) and symbol error rate (SER) can be achieved to perform parallel tasks, due to the richer dynamics and states of virtual nodes. The effect of system parameters on RC performance was also discussed. Our study would be helpful for the design and optimization of proposed parallel RC with optoelectronic feedback.

Automated summary

This study investigated the characteristics of reservoir computing using two mutually-coupled semiconductor lasers with optoelectronic feedback by implementing parallel tasks. It found that optimized performance is achieved around bifurcation points, and under optimized parameters, lower normalized mean squared error and symbol error rate can be achieved for parallel tasks. The study also discussed the influence of system parameters on reservoir computing performance, providing insights for design and optimization of parallel reservoir computing with optoelectronic feedback.