Multi-task photonic time-delay reservoir computing based on polarization modulation.

We propose and experimentally demonstrate a multi-task photonic time-delay reservoir computing (RC) system based on polarization modulation. The key component in the system is a polarization modulator (PolM) that functions, jointly with a polarization controller (PC) and a polarizer, as an equivalent Mach-Zehnder modulator (MZM) to perform electrical to optical conversion and to provide nonlinear operation. By adjusting the bias of the equivalent MZM, the nonlinear function can be optimized for different tasks to achieve the best multi-task performance. In this paper, the task-independent information processing capacity (IPC) of the time-delay RC system is evaluated. The results show that the readout bias of the equivalent MZM leads to a different IPC which can be optimized for different tasks. Two benchmark tasks (NARMA10 and IPIX radar signal prediction) are performed experimentally. The readout bias is adjusted independently for each of the two tasks to give a minimum normalized mean square error (NMSE), which are 0.2103 and 0.0031 for the NARMA10 and IPIX radar signal prediction tasks at a speed of 1.06 Mb/s, respectively.