Reservoir Computers with Random and Optimized Time-Shifts.

We investigate the effects of application of random time-shifts to the readouts of a reservoir computer in terms of both accuracy (training error) and performance (testing error). For both the cases of linear and nonlinear reservoirs and different choices of the reservoir parameters and different `tasks', we observe a substantial improvement in both accuracy and performance. We then develop a simple but effective optimization technique to optimize the choice of the time-shifts, which we test in numerical experiments.